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

Abstract

The invention discloses an underground cavern surrounding rock intelligent prediction analysis method, system and device, a storage medium and a program product, and the method comprises the steps: carrying out the surrounding rock classification of a current tunnel face of an underground cavern, obtaining the surrounding rock classification of the current tunnel face, carrying out the unfavorable geologic body prediction of a prediction cavern section based on the historical geophysical detection result data, and obtaining a prediction result. The method comprises the following steps: acquiring unfavorable geologic body forecast information, performing spatial distribution analysis according to the unfavorable geologic body forecast information, acquiring excavation spatial extension information of an underground cavity, and performing feature quantization on a current tunnel face surrounding rock category, the unfavorable geologic body forecast information and the excavation spatial extension information; inputting the characteristic quantification result into a surrounding rock category prediction model to perform surrounding rock category prediction; according to the method, high-precision prediction of the surrounding rock category is realized by combining the current tunnel face surrounding rock category, the unfavorable geologic body prediction information and the excavation space extension information, so that the accuracy of advanced geological prediction of the underground cavern is effectively improved, and the construction safety is powerfully guaranteed.

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 surrounding rock of an underground cavern. Background Art

[0002] With the development of the energy industry and the needs of urban construction, the construction of underground caverns is crucial for water conservancy and hydropower, railway and highway transportation, energy mining, and municipal engineering. Advanced geological prediction is an effective method to grasp 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, reasonably plan support measures, and improve the overall engineering 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 type of the unexplored tunnel 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 adopts 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 surrounding rock of underground caverns, the method comprising the following steps: 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; Based on the historical geophysical exploration results data, the predicted cave section of the underground cavern is predicted to have bad geological bodies, and bad geological body prediction information is obtained, wherein the historical geophysical exploration results data include seismic wave exploration results data and ground penetrating radar exploration results data, wherein the seismic wave exploration results data include wave velocity diagrams and seismic wave profile diagrams, and the ground penetrating radar exploration results data include ground penetrating radar profile diagrams; 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; 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; Performing feature quantification on the current tunnel face surrounding rock category, the bad geological body prediction information and the excavation space extension information to obtain feature quantification results, wherein the feature quantification results include the current tunnel face surrounding rock category value, the bad geological body development level value and the space 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 according to 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.

[0005] Optionally, before inputting the characteristic quantification result into a 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 development levels of unfavorable geological bodies, 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, wherein the initial neural network model includes: ; in, is an output sample, wherein the output sample includes a network value of a surrounding rock category label, is an input sample, which includes historical values ​​of surrounding rock categories, 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 are For the The connection weights between hidden neurons and output neurons, is the hidden neuron activation function, is the output neuron activation function, For the j The bias of the 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 prediction 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.

[0006] 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: 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.

[0007] Optionally, 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: A sparse cross entropy loss function is constructed, wherein the sparse cross entropy loss function includes: ; in, Represents 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; Calculate 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.

[0008] 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: Constructing a three-dimensional geological model of the underground cavern according to the engineering geological analysis data of the underground cavern; Obtaining current adverse geological body information of a current cave section of the underground cavern; Based on the bad geological body prediction information and the current bad geological body information, the bad geological body spatial distribution analysis is performed on the three-dimensional geological model to obtain a spatial distribution analysis result; 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.

[0009] Optionally, after inputting the characteristic quantification result into a 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, 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; When the predicted value of the surrounding rock category is greater than a first preset threshold, sending a first category engineering treatment strategy to a construction user corresponding to the underground cavern; When the surrounding rock category prediction value is greater than a second preset threshold value and less than or equal to the first preset threshold value, sending a second category engineering treatment strategy to the construction user, wherein the first preset threshold value is greater than the second preset threshold value; When the surrounding rock category prediction value is greater than a third preset threshold value and less than or equal to the second preset threshold value, sending a third category engineering treatment strategy to the construction user, wherein the second preset threshold value is greater than the third preset threshold value; 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.

[0010] 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: 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 is used to predict bad geological bodies for the predicted cave section of the underground cave based on historical geophysical exploration results data, and obtain bad 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 cave 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 forecast information of the adverse geological body, and obtain excavation space extension information of the underground cavern; A feature quantification module is used to perform feature quantification on the current tunnel face surrounding rock category, the bad geological body prediction information and the mining space extension information to obtain a feature quantification result, wherein the feature quantification result includes a current tunnel face surrounding rock category value, a bad geological body development level value and a space extension feature value; A surrounding rock category prediction module is used to input 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 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 surrounding rock category labels and surrounding rock category prediction values.

[0011] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent prediction and analysis device for underground cavern surrounding rock, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described above.

[0012] 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.

[0013] 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.

[0014] 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 the historical geophysical exploration results data, and obtains the 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 diagram and seismic wave profile diagram, and the ground penetrating radar detection results data includes ground penetrating radar profile diagram; the historical geophysical exploration results data of the underground cavern is obtained, and the bad geological body prediction information includes the bad geological body type and the spatial distribution information corresponding to the bad geological body type; the spatial distribution analysis of the underground cavern is performed according to the bad geological body prediction information to obtain the excavation space extension information of the underground cavern; the characteristics of the surrounding rock type of the current tunnel face, the bad 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 bad 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 the surrounding rock category prediction value, the surrounding rock category prediction model includes a mapping relationship table between the surrounding rock category label and the surrounding rock category prediction value; because the present invention predicts bad geological bodies based on seismic wave detection results and ground penetrating radar detection results, thereby improving the accuracy of bad geological body prediction, combining the current face surrounding rock category, bad geological body prediction information and excavation space extension information to predict the surrounding rock category, achieving high-precision prediction of the surrounding rock category, effectively improving the accuracy of advanced geological prediction of underground caverns, thereby effectively ensuring construction safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0016] Figure 1 It is a structural schematic diagram of an underground cavern surrounding rock intelligent prediction and analysis device in a hardware operating environment involved in an embodiment of the present invention; Figure 2 It is a schematic diagram of a flow chart of an embodiment of an intelligent prediction and analysis method for surrounding rock of underground caverns according to the present invention; Figure 3 It is a schematic diagram of the process of analyzing the excavation space extension information in an embodiment of the intelligent prediction and analysis method for surrounding rock of underground caverns of the present invention; Figure 4 It is a schematic diagram of the process of 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; Figure 5 It is a structural block diagram of an embodiment of an intelligent prediction and analysis system for underground cavern surrounding rock of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] Reference Figure 1 , Figure 1 The present invention 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 the embodiment of the present invention.

[0020] like Figure 1 As shown, the underground cavern surrounding rock intelligent prediction and analysis device 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. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0021] 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 surrounding rock of underground caverns, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0022] 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 rocks.

[0023] 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.

[0024] The embodiment of the present invention provides an intelligent prediction and analysis method for surrounding rock of underground caverns, referring to Figure 2 , Figure 2 It is a schematic diagram of the flow of an embodiment of an intelligent prediction and analysis method for underground cavern surrounding rock of the present invention.

[0025] In this embodiment, the underground cavern surrounding rock intelligent prediction and analysis method comprises the following steps: 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.

[0026] It should be noted that the present embodiment can be applied to the advanced geological forecast of underground caverns, which can promote the rapid development of the digitalization and refinement of geological analysis and geological prediction technologies in the construction of underground caverns. Among them, the advanced geological forecast can be an advanced forecast of the surrounding rock and stratum conditions in front of and around the heading face when excavating the underground cavern.

[0027] It should be understood that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a terminal electronic device capable of realizing the above functions, etc. The following takes the underground cavern surrounding rock intelligent prediction and analysis device (hereinafter referred to as the analysis device) as an example to illustrate this embodiment and the following embodiments.

[0028] It should be noted that the current tunnel face may be the tunnel face of the currently explored tunnel section in the underground cavern. The analysis device may classify the surrounding rock types of the current tunnel face that has been explored in the current tunnel section to obtain the surrounding rock type of the current tunnel face.

[0029] Step S20: predicting the unfavorable geological body of the predicted cave section of the underground cavern based on the historical geophysical exploration results data to obtain unfavorable geological body prediction information.

[0030] It should be noted that the predicted cave section may be a cave section of the 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 cave section based on the current cave section that has been explored in the underground cavern to obtain adverse geological body prediction information.

[0031] 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 the spatial distribution information corresponding to the unfavorable geological body types.

[0032] 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.

[0033] 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.

[0034] It should be noted that the analysis equipment can obtain historical geophysical exploration results data through geophysical exploration methods. The geophysical exploration methods used in this embodiment include seismic wave method (a method of long-distance advance exploration) and ground penetrating radar method (a method of short-distance advance exploration). Therefore, the geophysical exploration results involved include seismic wave method exploration results and ground penetrating radar exploration results. Seismic wave method exploration results include: longitudinal wave velocity diagram, shear wave velocity diagram, seismic profile diagram (time-distance two-dimensional image); ground penetrating radar method exploration results include: radar profile diagram (time-distance two-dimensional image).

[0035] It should be noted that the preprocessing includes static correction processing, denoising processing, dynamic correction processing, time-to-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 propagation time differences and enhance effective wave energy; depth conversion processing can be time-to-depth conversion, which is used to calculate the depth based on the electromagnetic wave velocity.

[0036] In some embodiments, the analysis equipment selects a suitable observation method and related observation parameters according to the geological conditions and structural conditions of the surrounding rock; collects data according to the design plan of the observation system; and performs pre-processing such as static correction, denoising, dynamic correction, time-depth conversion, and normalization on the collected data due to the complexity of the on-site construction environment and the different types, formats, and time dimensions of the collected data, to obtain geophysical exploration results data.

[0037] 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.

[0038] 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 abnormal feature information may include abnormal frequency features and abnormal amplitude features in the ground penetrating radar features; the seismic wave abnormal feature information may include abnormal wave velocity features, abnormal frequency features and abnormal amplitude features in the seismic wave features.

[0039] It can be understood that the analysis equipment can analyze the signal characteristics of the 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 cause the above-mentioned signal characteristics are analyzed, including: whether there are unfavorable geological bodies, the types of unfavorable geological bodies, and the spatial distribution of unfavorable geological bodies, and the geological conditions in front of the face are interpreted; finally, the surrounding rock classification results are given.

[0040] Taking the seismic wave method as an example: the longitudinal wave velocity of the seismic wave in the section of pile number J0+400~J0+500 is between 2600m / s and 3200m / s, and the overall surrounding rock conditions are equivalent to the current tunnel face conditions; the reflection signal of the section of pile number J0+438~J0+463 is strong, the frequency is low, and the amplitude is large, which indicates that there is rich water in this area. The rock mass quality of the section of pile number J0+400~J0+500 is Grade III, and the rock mass quality of the section of pile number J0+438~J0+463 is Grade IV, so attention should be paid during excavation.

[0041] In some embodiments, the analysis device can analyze whether there are places in the result data where the signal characteristics differ from the surrounding rock signal characteristics; if so, analyze the possible causes of the signal change and determine the type of bad geological body that caused the signal change; delineate the contours of the bad geological body: for the seismic wave method result data, the wave velocity reduction, the reflection wave event axis misalignment, and the amplitude mutation area may be the boundary of the bad geological body; for the ground penetrating radar method result data, the reflection wave event axis misalignment and the amplitude mutation area may be the boundary of the bad geological body. Finally, based on the geological interpretation results of the geophysical exploration result data, the preliminary conclusions of the geophysical exploration analysis are obtained, such as the possible types of bad geological bodies and spatial distribution information, and the surrounding rock categories of the geophysical exploration analysis.

[0042] 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, and 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.

[0043] Step S30: performing spatial distribution analysis on the underground cavern according to the prediction information of the adverse geological body to obtain excavation space extension information of the underground cavern.

[0044] It should be noted that the above excavation space extension information may be the spatial extension information of the structure predicted and revealed by the previous excavation. The excavation space extension information may include the excavated length, the time point when a specific geological layer is reached, the spatial distribution information of the adverse geological bodies revealed by the excavation, etc.

[0045] 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 an embodiment. The above step S30 may include: Step S301: constructing a three-dimensional geological model of the underground cavern according to the engineering geological analysis data of the underground cavern; Step S302: obtaining current adverse geological body information of the current cave section of the underground cavern; 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; 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.

[0046] It can be understood that the analysis equipment can conduct spatial distribution analysis on the previously speculated adjacent unfavorable geological bodies and the exposed adjacent unfavorable geological bodies of the underground caverns 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 caverns.

[0047] In some embodiments, the analysis equipment can obtain engineering geological analysis data of underground caverns, 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, 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 forecast information, and obtain the excavation space extension information of the underground cavern.

[0048] Step S40: performing feature quantification on the current tunnel face surrounding rock type, the adverse geological body prediction information and the mining space extension information to obtain feature quantification results.

[0049] It should be noted that the characteristic quantification results include the current tunnel face surrounding rock category value, the unfavorable geological body development level value and the spatial extension characteristic value.

[0050] 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 input layer values ​​of the neural network 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, as shown in Table 1 below. Table 1 is a surrounding rock category mapping relationship table.

[0051] Table 1, surrounding rock category mapping table

[0052] In some embodiments, according to the geophysical advance detection analysis results and geological exploration analysis results, the development of the bad geological body in front of the tunnel face, including the type of bad geological body and the possibility of existence, can be obtained. The system divides the bad geological body development level value into 4 input layers, namely the fault development level value, the water-rich development level value, the cave development level value and the soft rock development level value, and converts the geophysical advance detection analysis results and the geological exploration analysis results into corresponding values ​​as the neural network input layer values ​​according to the following Table 2. For example, the bad geological body development level value is divided into: 0~25% corresponds to the non-existence of the bad geological body, 25~50% (including 25%) corresponds to the low possibility of the existence of the bad geological body, 50~75% (including 50%) corresponds to the high possibility of the existence of the bad geological body, and 75~100% (including 75%) corresponds to the existence of the bad geological body. The bad geological body development level value is taken with reference to the following Table 2, which is a quantitative table of the bad geological body development level.

[0053] Table 2. Quantitative table of development level of unfavorable geological bodies

[0054] In some embodiments, the spatial extension characteristic value may be the spatial extension characteristic value of the structure speculated in the early excavation and revealed by the excavation. The analysis device may 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 with the following Table 3, which is a quantification table of spatial extension characteristics.

[0055] Table 3, Quantization table of spatial extension features

[0056] Step S50: inputting the characteristic quantification result into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section.

[0057] 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 quantization 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 surrounding rock category labels and surrounding rock category prediction values.

[0058] 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.

[0059] It can be understood that this embodiment predicts the type of unfavorable geological body in the predicted tunnel section to obtain 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 ahead of the face of the underground cavern based on the prediction information of the unfavorable geological body in 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.

[0060] Furthermore, in order to improve the prediction accuracy of surrounding rock types, Figure 4 , Figure 4 In one embodiment, a schematic diagram of a process for constructing a surrounding rock type prediction model is shown. Before the above step S50, the following steps may be included: Step S51: Acquire historical sample data of underground caverns; Step S52: performing data cleaning on the historical sample data to obtain initial sample data; Step S53: normalizing the initial sample data, and performing time-series alignment on the normalized initial sample data to obtain target sample data; Step S54: constructing an initial neural network model, and initializing the weights and biases of the initial neural network model; Step S55: constructing a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values; 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.

[0061] 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 development levels of unfavorable geological bodies 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.

[0062] It should be noted that the initial neural network model includes: ; in, is an output sample, wherein the output sample includes a surrounding rock category label network value, which can be converted into a surrounding rock category prediction value, is an input sample, which includes historical values ​​of surrounding rock categories, 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 are For the The connection weights between hidden neurons and output neurons, is the hidden neuron activation function, is the output neuron activation function, For the j The bias of the hidden neurons, For the k The bias of the output neuron.

[0063] In some embodiments, the neural network includes three layers: an input layer, a hidden layer, and an output layer. The input layer has 6 input nodes by default: They correspond to the category value of the surrounding rock of the face, the value of the fault development level, the value of the water-rich development level, the value of the cave development level, the value of the soft rock development level, the spatial extension characteristic value of the structure speculated in the early excavation, and the structure revealed by the excavation. After the input layer receives the sample input data, it combines the input data with the weight and bias, inputs the result into the hidden layer, and processes it through the hidden neuron activation function to obtain the output result, which is then combined with the corresponding weight and bias, processed through the output neuron activation function, and outputs the final result in the output layer.

[0064] In some embodiments, data cleaning may include denoising the historical sample data, filling missing data, etc. The analysis device may use a Min-Max normalization model to normalize the historical sample data. The Min-Max normalization model includes: ; 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.

[0065] 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 spatial extension characteristics of structures speculated in the early excavation and revealed by the excavation; the historical sample input data is preprocessed to initialize the weights and biases of the preliminary neural network model, and the historical sample input data in the training set after preprocessing is used 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.

[0066] Furthermore, in order to improve the model performance and thus improve the prediction accuracy of surrounding rock types, in some embodiments, the above step S56 may include: Step S561: training the initialized neural network model based on the mapping relationship table and the target sample data; Step S562: inputting the historical input data into the trained neural network model to obtain the surrounding rock category label network value; Step S563: Calculate 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; Step S564: determining whether the deviation value is within a preset deviation range; 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; Step S566: If the deviation value is not within the preset deviation range, return to execute the step of training the initialized neural network model based on the mapping relationship table and the target sample data.

[0067] 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.

[0068] Furthermore, in order to accurately calculate the deviation value and improve the prediction accuracy of the model, in some embodiments, the above step S563 may include: Step S5631: construct a sparse cross entropy loss function; Step S5632: Calculating an average loss value based on the sparse cross entropy loss function; 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.

[0069] In some embodiments, the analysis device may embed a loss function into a neural network model. When constructing the neural network model, a loss function is set to measure the difference between the model prediction result and the true label, thereby improving the model prediction accuracy by minimizing the calculated value of the loss function operation.

[0070] 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 loss function calculation value. The sparse cross entropy loss function includes: ; in, The number of samples representing historical sample data (i.e., the number of data combinations of the tunnel face surrounding rock category values, the development level of unfavorable geological bodies, the spatial extension characteristic values ​​of the structures speculated in the previous excavation, and revealed by the excavation, which are input into the model); Represents the sample index, which is used to traverse all samples, and the value range is from 1 to N; Represents the true label, which 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 Probability of class; 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 is.

[0071] In some embodiments, the analysis device can update the weight parameters, bias parameters and learning rate of the model through continuous iterative training, and calculate the mean square error, and stop training when the mean square error is within the allowable range or the number of iterations exceeds a threshold. The termination condition of this training iteration is: the mean square error is less than 0.0001 or the maximum number of iterations of the model training exceeds 1000 times.

[0072] In some embodiments, the analysis device uses the test sample to test the accuracy of the aforementioned trained model. The specific operation steps are as follows: input the test sample into the model to obtain the predicted value of the surrounding rock category, compare it with the actual measured surrounding rock category reference value, and calculate the mean square error of the two and determine whether the mean square error is within the allowable range. If the mean square error is within the allowable range, it means that the model training is successful. If the mean square error is outside the allowable range, the network is retrained.

[0073] Furthermore, in order to improve construction safety, after the above step S50, the following steps are further included: 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; Step S71: When the surrounding rock category prediction value is greater than a first preset threshold, a first category engineering treatment strategy is sent to a construction user corresponding to the underground cavern; Step S72: When the surrounding rock category prediction value is greater than a second preset threshold value and less than or equal to the first preset threshold value, sending a second category engineering treatment strategy to the construction user, wherein the first preset threshold value is greater than the second preset threshold value; Step S73: When the surrounding rock category prediction value is greater than a third preset threshold value and less than or equal to the second preset threshold value, sending a third category engineering treatment strategy to the construction user, wherein the second preset threshold value is greater than the third preset threshold value; 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.

[0074] 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 are pipe shed, shotcrete, system anchors, steel frames, and secondary support when necessary.

[0075] 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 frames.

[0076] The third preset threshold may be 2.00, corresponding to surrounding rock categories III1 and III2. The third category engineering treatment strategies may include: support types are shotcrete, system anchors plus steel mesh, and when the span of the face is large, concrete lining is poured.

[0077] The fourth preset threshold may be 0, corresponding to surrounding rock categories I and II. The fourth category engineering treatment strategies may include: the support type is unsupported or local anchors or shotcrete. When the span of the face is large, shotcrete, system anchors and steel mesh are used.

[0078] 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 bad geological body of the predicted tunnel section of the underground cavern based on the historical geophysical exploration results data, and obtains the 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 diagram and seismic wave profile diagram, and the ground penetrating radar detection results data includes ground penetrating radar profile diagram; the historical geophysical exploration results data of the underground cavern is obtained, and the bad geological body prediction information includes the bad geological body type and the spatial distribution information corresponding to the bad geological body type; the spatial distribution analysis of the underground cavern is performed according to the bad geological body prediction information to obtain the excavation space extension information of the underground cavern; the characteristics of the surrounding rock type of the current tunnel face, the bad 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 bad 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 the surrounding rock category prediction value, the surrounding rock category prediction model includes a mapping relationship table between the surrounding rock category label and the surrounding rock category prediction value; since this embodiment predicts bad geological bodies based on seismic wave detection results and ground penetrating radar detection results, thereby improving the accuracy of bad geological body prediction, the surrounding rock category prediction is performed in combination with the current face surrounding rock category, bad geological body prediction information and excavation space extension information, so as to achieve high-precision prediction of surrounding rock categories, effectively improve the accuracy of advanced geological prediction of underground caverns, thereby effectively ensuring construction safety.

[0079] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which is stored a program for intelligent prediction and analysis of underground cavern surrounding rock. When the program for intelligent prediction and analysis of underground cavern surrounding rock is executed by a processor, the steps of the method for intelligent prediction and analysis of underground cavern surrounding rock as described above are implemented.

[0080] The computer-readable storage medium provided in the present application 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 of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0081] The above-mentioned computer-readable storage medium may be included in the intelligent prediction and analysis device for the surrounding rock of underground caverns; or it may exist independently without being assembled into the intelligent prediction and analysis device for the surrounding rock of underground caverns.

[0082] 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.

[0083] The specific implementation methods of the computer program product of the present invention are basically the same as the above-mentioned embodiments of the intelligent prediction and analysis method for surrounding rock of underground caverns, and will not be repeated here.

[0084] Reference Figure 5 , Figure 5 It is a structural block diagram of an embodiment of an intelligent prediction and analysis system for underground cavern surrounding rock of the present invention.

[0085] like Figure 5 As shown, the underground cavern surrounding rock intelligent prediction and analysis system proposed in the embodiment of the present invention includes: 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; The bad geological body prediction module 20 is used to predict the bad geological body of the predicted cave section of the underground cave based on the historical geophysical exploration results data, and obtain the 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 diagram and seismic wave profile diagram, the ground penetrating radar detection results data includes ground penetrating radar profile diagram; the historical geophysical exploration results data of the underground cave is obtained, and the bad geological body prediction information includes the bad geological body type and the spatial distribution information corresponding to the bad geological body type; A spatial distribution analysis module 30 is used to perform spatial distribution analysis on the underground cavern according to the bad geological body prediction information to obtain excavation space extension information of the underground cavern; The feature quantification module 40 is used to perform feature quantification on the current tunnel face surrounding rock category, the bad geological body prediction information and the mining space extension information to obtain a feature quantification result, wherein the feature quantification result includes a current tunnel face surrounding rock category value, a bad geological body development level value and a space extension feature value; 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 according to 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 surrounding rock category labels and surrounding rock category prediction values.

[0086] 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 bad geological body of the predicted tunnel section of the underground cavern based on the historical geophysical exploration results data, and obtains the 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 diagram and seismic wave profile diagram, and the ground penetrating radar detection results data includes ground penetrating radar profile diagram; the historical geophysical exploration results data of the underground cavern is obtained, and the bad geological body prediction information includes the bad geological body type and the spatial distribution information corresponding to the bad geological body type; the spatial distribution analysis of the underground cavern is performed according to the bad geological body prediction information to obtain the excavation space extension information of the underground cavern; the characteristics of the surrounding rock type of the current tunnel face, the bad 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 bad 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 the surrounding rock category prediction value, the surrounding rock category prediction model includes a mapping relationship table between the surrounding rock category label and the surrounding rock category prediction value; since this embodiment predicts bad geological bodies based on seismic wave detection results and ground penetrating radar detection results, thereby improving the accuracy of bad geological body prediction, the surrounding rock category prediction is performed in combination with the current face surrounding rock category, bad geological body prediction information and excavation space extension information, so as to achieve high-precision prediction of surrounding rock categories, effectively improve the accuracy of advanced geological prediction of underground caverns, thereby effectively ensuring construction safety.

[0087] The underground cavern surrounding rock intelligent prediction and analysis system provided by the present application adopts the underground cavern surrounding rock intelligent prediction and analysis method in the above-mentioned embodiment, which can solve the technical problems of underground cavern surrounding rock intelligent prediction and analysis. Compared with the prior art, the beneficial effects of the underground cavern surrounding rock intelligent prediction and analysis system provided by the present application are the same as the beneficial effects of the underground cavern surrounding rock intelligent prediction and analysis method provided by the above-mentioned embodiment, and other technical features of the underground cavern surrounding rock intelligent prediction and analysis system are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0088] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0089] 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 them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0090] In addition, for technical details not fully described in this embodiment, reference can be made 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.

[0091] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0092] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0093] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a 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, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0094] 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 specification 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 surrounding rock of underground caverns, characterized in that: The underground cavern surrounding rock intelligent prediction and analysis method comprises: 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; Based on the historical geophysical exploration results data, the predicted cave section of the underground cavern is predicted to have bad geological bodies, and bad geological body prediction information is obtained, wherein the historical geophysical exploration results data include seismic wave exploration results data and ground penetrating radar exploration results data, wherein the seismic wave exploration results data include wave velocity diagrams and seismic wave profile diagrams, and the ground penetrating radar exploration results data include ground penetrating radar profile diagrams; 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; 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; Performing feature quantification on the current tunnel face surrounding rock category, the bad geological body prediction information and the excavation space extension information to obtain feature quantification results, wherein the feature quantification results include the current tunnel face surrounding rock category value, the bad geological body development level value and the space 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 according to 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 surrounding rock of underground caverns 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 development levels of unfavorable geological bodies, 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, wherein the initial neural network model includes: ； in, is an output sample, wherein the output sample includes a network value of a surrounding rock category label, is an input sample, which includes historical values ​​of surrounding rock categories, 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 are For the The connection weights between hidden neurons and output neurons, is the hidden neuron activation function, is the output neuron activation function, For the j The bias of the 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 prediction 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 surrounding rock of underground caverns 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 method for intelligent prediction and analysis of surrounding rock of underground caverns 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: A sparse cross entropy loss function is constructed, wherein the sparse cross entropy loss function includes: ； in, Represents 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; Calculate 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 method for intelligent prediction and analysis of surrounding rock of underground caverns according to any one of claims 1 to 4, characterized in that: The performing of 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: Constructing a three-dimensional geological model of the underground cavern according to the engineering geological analysis data of the underground cavern; Obtaining current adverse geological body information of a current cave section of the underground cavern; Based on the bad geological body prediction information and the current bad geological body information, the bad geological body spatial distribution analysis is performed on the three-dimensional geological model to obtain a spatial distribution analysis result; 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.

6. The method for intelligent prediction and analysis of surrounding rock of underground caverns according to any one of claims 1 to 4, characterized in that: After the characteristic quantification result is input 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, 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; When the predicted value of the surrounding rock category is greater than a first preset threshold, sending a first category engineering treatment strategy to a construction user corresponding to the underground cavern; When the surrounding rock category prediction value is greater than a second preset threshold value and less than or equal to the first preset threshold value, sending a second category engineering treatment strategy to the construction user, wherein the first preset threshold value is greater than the second preset threshold value; When the surrounding rock category prediction value is greater than a third preset threshold value and less than or equal to the second preset threshold value, sending a third category engineering treatment strategy to the construction user, wherein the second preset threshold value is greater than the third preset threshold value; 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.

7. An intelligent prediction and analysis system for underground cavern surrounding rock, characterized in that: The underground cavern surrounding rock intelligent prediction and analysis system comprises: 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 is used to predict bad geological bodies for the predicted cave section of the underground cave based on historical geophysical exploration results data, and obtain bad 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 cave 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 forecast information of the adverse geological body, and obtain excavation space extension information of the underground cavern; A feature quantification module is used to perform feature quantification on the current tunnel face surrounding rock category, the bad geological body prediction information and the mining space extension information to obtain a feature quantification result, wherein the feature quantification result includes a current tunnel face surrounding rock category value, a bad geological body development level value and a space extension feature value; A surrounding rock category prediction module is used to input 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 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 surrounding rock category labels and surrounding rock category prediction values.

8. An intelligent prediction and analysis device for underground cavern surrounding rock, characterized in that: The underground cavern surrounding rock intelligent prediction and analysis device includes: a memory, a processor, and an underground cavern surrounding rock intelligent prediction and analysis program stored in the memory and executable on the processor, wherein the underground cavern surrounding rock intelligent prediction and analysis program is configured to implement the underground cavern surrounding rock intelligent prediction and analysis method as described in any one of claims 1 to 6.

9. 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 as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes 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 steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described in any one of claims 1 to 6 are implemented.

Images