Method for judging support stability of compressed air energy storage cavern

Abstract

The application provides a compressed air energy storage cavern support stability discrimination method, and relates to the technical field of cavern support, and the specific steps include: collecting the mechanical parameters and influence parameters of the cavern support sample and the support to be discriminated, constructing a current adversarial network, extracting the pre-training model parameters in the database through migration learning and initializing, generating simulation parameters through training; constructing a heat-flow-solid coupling finite element simulation model based on the measured data, calibrating the model by using the simulation parameters; inputting the influence parameters of the support to be discriminated into the calibrated model, obtaining the mechanical parameters and extracting characteristic parameters such as the maximum stress, strain and anchor rod axial force; generating a safety coefficient through data processing, and comprehensively evaluating the support stability. The application constructs a multi-dimensional data evaluation system, realizes comprehensive monitoring of complex physical phenomena such as heat-force coupling, seepage-stress hysteresis and the like in the operation of the cavern, can accurately evaluate the real stress state of the cavern, and can predict potential risks in advance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine support, in particular to a compressed air energy storage mine support stability discrimination method. BACKGROUND

[0002] As the core facility for storing compressed air, the stability of the support structure of the compressed air energy storage mine directly relates to the safety and reliability of the energy storage system. During the operation of the mine, not only does it bear static loads such as the self-weight of the surrounding rock and the ground stress, but also faces complex dynamic conditions such as thermal-mechanical coupling and seepage-stress coupling caused by the charging and discharging cycle of compressed air, making the stress state of the support structure extremely complex. The existing technology lacks analysis and research on the stability discrimination of the support structure.

[0003] In the prior art, a stability discrimination method for the initial support of the underground gas storage chamber of a compressed air energy storage power station is provided in CN115203780A, which includes the following steps: considering the swelling force and softening property of the hydrophilic surrounding rock of the underground gas storage chamber, drawing the surrounding rock response curve during the humidification process; obtaining the support parameters of the underground gas storage chamber, calculating and drawing the support structure characteristic curve; combining the surrounding rock response curve and the support characteristic curve to determine the coordinates of the intersection point of the two curves, and obtaining the equilibrium support force of the hydrophilic surrounding rock and the support when they are in equilibrium according to the coordinates of the intersection point; calculating the safety factor of the underground gas storage chamber according to the equilibrium support force and the limit support force; and judging the stability state of the chamber according to the safety factor. This method fully considers the swelling force, softening property of the surrounding rock and the support force effect in the relationship between the surrounding rock and the support, and uses the safety factor as the stability index of the underground gas storage chamber. It is suitable for the stability evaluation of underground chambers with complex surrounding rock characteristics, and the discrimination method is accurate and efficient.

[0004] However, there are still the following deficiencies. As can be seen from the above statements, the existing technology cannot meet the stability discrimination requirements of compressed air energy storage mines under complex working conditions. First, the data dimension is single, only focusing on the swelling force and softening property of the hydrophilic surrounding rock, without considering the influence of key dynamic parameters such as temperature variation amplitude, charging / discharging cycle length, etc. on the mechanical properties of the surrounding rock during the operation of the compressed air energy storage mine, as well as complex physical phenomena such as thermal-mechanical coupling and seepage-stress hysteresis, resulting in the inability to fully reflect the real stress state of the mine. Second, the analysis method has great limitations. The discrimination method based on curve combination and safety factor calculation is essentially a traditional analytical method, which relies on simplified mechanical models and assumptions, and cannot accurately depict the complex mechanical behavior of the support structure and the surrounding rock under the action of multiple physical fields. When facing nonlinear and dynamically changing working conditions, the accuracy of the discrimination result is low. Third, there is a lack of model calibration and optimization mechanism. There is no effective correlation with actual working condition data, and the discrimination model cannot be calibrated and optimized according to real-time monitoring data or simulation results, making it difficult to adapt to the support stability discrimination requirements under different operating conditions.

[0005] The above information disclosed in the background section is only for the purpose of enhancing the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide a compressed air energy storage cavern support stability discrimination method to solve the problems raised in the background art.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0008] A compressed air energy storage cavern support stability discrimination method, the specific steps comprising:

[0009] S1. Collect the support samples of the cavern and the mechanical parameters and influence parameters of the support to be discriminated, construct a current adversarial network for the mechanical parameters and influence parameters of the cavern, extract a pre-trained adversarial network from a database, migrate model parameters to the current adversarial network, and complete the parameter initialization of the current adversarial network, train the current adversarial network with the mechanical parameters and influence parameters to obtain simulated mechanical parameters and corresponding simulated influence parameters, the influence parameters including the elastic modulus of surrounding rock, the thermal expansion coefficient, the temperature variation amplitude of single cycle, the single inflation / deflation cycle duration, the reference consolidation time at normal temperature, the influence coefficient of temperature on consolidation time, the difference between the current working condition temperature and the normal temperature, and the thermal-mechanical coupling risk coefficient and seepage-stress hysteresis coefficient based on the above parameters;

[0010] S2. Construct a thermal-flow-solid coupling finite element simulation model based on the mechanical parameters and influence parameters of the support samples, and calibrate the simulation model based on the simulated mechanical parameters and corresponding simulated influence parameters;

[0011] S3. Input the influence parameters of the support to be discriminated into the calibrated simulation model to obtain the mechanical parameters of the support to be discriminated;

[0012] S4. Extract feature parameters from the mechanical parameters of the support to be discriminated to obtain the maximum stress value, the maximum strain value and the maximum axial force value of the anchor rod;

[0013] S5. Perform data processing on the maximum stress, maximum strain and maximum axial force value of the anchor rod of the support to be discriminated respectively to generate the stress safety factor, strain safety factor and anchor rod axial force safety factor of the support to be discriminated;

[0014] S6. According to the stress safety factor, strain safety factor and anchor rod axial force safety factor of the support to be discriminated, evaluate the stability state of the support to be discriminated.

[0015] Further, the mechanical parameters include stress value, strain value and axial force value of the anchor rod.

[0016] Furthermore, we extract the pre-trained adversarial network from the database and transfer the model parameters to the current adversarial network. The specific steps are as follows:

[0017] In the process of extracting pre-trained adversarial networks, a dynamic similarity matching algorithm is introduced to construct feature vectors based on the influencing parameters. Based on the feature vectors, the Euclidean distance between the influencing parameters of the pre-trained adversarial network and the current adversarial network is calculated to screen out the pre-trained adversarial networks with the top three similarities.

[0018] The Euclidean distance between the influencing parameters of the pre-trained adversarial network and the current adversarial network is calculated based on the following formula:

[0019] ;

[0020] in, For the The Euclidean distance between the influencing parameters of the pre-trained adversarial network and the current adversarial network, that is, the similarity between the pre-trained adversarial network and the current adversarial network;

[0021] Where, For the The first Influencing parameters, The current adversarial network Influencing parameters, is the index of the pre-trained adversarial network, is the index of the influencing parameter, , They correspond to the elastic modulus of the surrounding rock, the thermal expansion coefficient, the temperature variation range of a single cycle, the duration of a single inflation / deflation cycle, the benchmark consolidation time at room temperature, the influence coefficient of temperature on consolidation time, the difference between the current working temperature and the room temperature, the thermal-mechanical coupling risk coefficient, and the seepage-stress hysteresis coefficient.

[0022] A weighted fusion migration method is used to assign corresponding weights to each pre-trained adversarial network according to the similarity between it and the current adversarial network, and the parameters of multiple pre-trained adversarial networks are superimposed and migrated to the current adversarial network according to the weights.

[0023] The parameters of the pre-trained adversarial network are the weight matrix of the generator, the bias vector of the generator, the weight matrix of the discriminator, and the bias vector of the discriminator;

[0024] The top three pre-trained adversarial networks in terms of similarity are pre-trained adversarial network A, pre-trained adversarial network B, and pre-trained adversarial network C. The weight coefficient of each pre-trained adversarial network is determined according to its similarity with the current adversarial network. The higher the similarity, the greater the weight coefficient.

[0025] ;

[0026] wherein, is the i-th parameter of the current adversarial network, is the i-th parameter of the pre-trained adversarial network A, is the i-th parameter of the pre-trained adversarial network B, is the i-th parameter of the pre-trained adversarial network C, is the i-th parameter of the pre-trained adversarial network A, is the i-th parameter of the pre-trained adversarial network B, is the i-th parameter of the pre-trained adversarial network C, is the weight coefficient of the pre-trained adversarial network A, is the weight coefficient of the pre-trained adversarial network B, is the weight coefficient of the pre-trained adversarial network C, is the index of the pre-trained adversarial network parameter, , respectively correspond to the weight matrix of the generator, the bias vector of the generator, the weight matrix of the discriminator and the bias vector of the discriminator, on the basis of , .

[0027] Further, the thermal-force coupling risk coefficient is calculated, and the formula is as follows:

[0028] ;

[0029] wherein, is the thermal-force coupling risk coefficient;

[0030] in the formula, is the elastic modulus of the support, is the thermal expansion coefficient, is the temperature change amplitude of a single cycle, is the length of a single inflation / deflation cycle.

[0031] Further, the seepage-stress hysteresis coefficient is calculated, and the formula is as follows:

[0032] ;

[0033] wherein, is the seepage-stress hysteresis coefficient;

[0034] in the formula, is the reference consolidation time at normal temperature, is the temperature influence coefficient on the consolidation time, is the difference between the current working temperature and the normal temperature.

[0035] Further, the stability coefficient of the support to be judged is obtained, and the formula is as follows:

[0036] ;

[0037] ;

[0038] ;

[0039] ;

[0040] wherein, is the stability coefficient of the support to be judged;

[0041] In the formula, is the stress safety factor, is the strain safety factor, is the anchor rod axial force safety factor, is the maximum stress that the support can bear, is the maximum strain that the support can bear, is the maximum axial force allowed when the anchor rod is designed, is the maximum stress value of the support, is the maximum strain value of the support, is the maximum axial force value of the anchor rod.

[0042] Further, the specific process of step S6 is as follows:

[0043] The stability of the support is determined by the minimum value of the stress safety factor , the strain safety factor , and the anchor rod axial force safety factor When any of the indicators does not meet the safety requirement, the support will be unstable;

[0044] When , it means that all three safety factors are greater than 1, so the ultimate bearing capacity of the support is greater than the actual load, and the support is stable;

[0045] When , it means that at least one of the three safety factors is equal to 1, so the actual load of the support reaches the ultimate bearing capacity, and the support is close to failure;

[0046] When , it means that at least one of the three safety factors is less than 1, so the actual load of the support exceeds the ultimate bearing capacity, and the support is unstable.

[0047] Among them, "1" is the mathematical representation of the equal ultimate capacity and actual load, and is also the dividing point between stability and instability.

[0048] Compared with the prior art, the beneficial effects of the present application are:

[0049] The present application collects multiple index mechanical parameters such as elastic modulus of surrounding rock, thermal expansion coefficient, single cycle temperature variation amplitude and influence parameters thereof, constructs a multi-dimensional data evaluation system through calculation of quantitative indexes such as thermal-mechanical coupling risk coefficient and seepage-stress hysteresis coefficient, improves the comprehensive monitoring of complex physical phenomena such as thermal-mechanical coupling and seepage-stress hysteresis in the operation of the chamber, can accurately evaluate the real stress state of the chamber, and can predict potential risks in advance, calibrates the thermal-flow-solid coupling finite element simulation model based on the simulated mechanical parameters and the corresponding simulated influence parameters, can continuously optimize the model according to the actual working condition data, makes the model adapt to the support stability discrimination needs under different geological conditions and operation conditions, and enhances the universality of the model.

[0050] By constructing the current adversarial network, the simulated mechanical parameters are obtained by using transfer learning and adversarial training, the thermal-flow-solid coupling finite element simulation model is calibrated, the self-adaptive ability of machine learning and the physical modeling advantage of finite element analysis are combined, the adaptability to nonlinear and dynamic change conditions is significantly improved, the mechanical behavior analysis of the support structure and the surrounding rock is more in line with the actual situation, and the accuracy of the stability discrimination result is effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 It is a whole method flowchart of the present application;

[0052] Figure 2 It is a fitting curve graph of the elastic modulus and the thermal-mechanical coupling risk coefficient of the present application;

[0053] Figure 3 It is a fitting curve graph of the thermal expansion coefficient and the thermal-mechanical coupling risk coefficient of the present application;

[0054] Figure 4 It is a fitting curve graph of the single cycle temperature variation amplitude and the thermal-mechanical coupling risk coefficient of the present application;

[0055] Figure 5 It is a fitting curve graph of the single inflation / deflation cycle length and the thermal-mechanical coupling risk coefficient of the present application;

[0056] Figure 6 It is a fitting curve graph of the reference consolidation time and the seepage-stress hysteresis coefficient of the present application;

[0057] Figure 7 It is a fitting curve graph of the single inflation / deflation cycle length and the seepage-stress hysteresis coefficient of the present application;

[0058] Figure 8 It is a fitting curve graph of the temperature influence coefficient on the consolidation time and the seepage-stress hysteresis coefficient of the present application;

[0059] Figure 9A fitting curve diagram of the difference between the current working temperature and the normal temperature of the present application and the seepage-stress hysteresis coefficient. DETAILED DESCRIPTION

[0060] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0061] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the usual meanings understood by those skilled in the art to which the present application belongs. The terms "first", "second", and similar terms used in the present application do not represent any order, number, or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right", and the like only represent relative positional relationships, which can change accordingly when the absolute position of the described object changes.

[0062] Example 1

[0063] Please refer to Figures 1 to 9 The present application provides a technical solution:

[0064] A compressed air energy storage cavern support stability discrimination method, the specific steps comprising:

[0065] S1. Collect the support sample of the cavern and the mechanical parameters and influence parameters of the support to be discriminated, construct a current adversarial network for the mechanical parameters and influence parameters of the cavern, extract a pre-trained adversarial network from a database, migrate model parameters to the current adversarial network, and complete parameter initialization of the current adversarial network, train the current adversarial network using the mechanical parameters and influence parameters to obtain simulated mechanical parameters and corresponding simulated influence parameters, the influence parameters including the elastic modulus of surrounding rock, the thermal expansion coefficient, the temperature variation amplitude of a single cycle, the single inflation / deflation cycle duration, the reference consolidation time at normal temperature, the influence coefficient of temperature on consolidation time, the difference between the current working temperature and the normal temperature, and the thermal-mechanical coupling risk coefficient and the seepage-stress hysteresis coefficient based on the above parameters;

[0066] On the basis of the above embodiment, the mechanical parameters include stress value, strain value, and shaft force value of the anchor rod.

[0067] On the basis of the above embodiments, the stress value, strain value, anchor rod axial force value, surrounding rock elastic modulus, thermal expansion coefficient, single cycle temperature change amplitude, single inflation / deflation cycle duration, reference consolidation time at normal temperature, temperature influence coefficient on consolidation time, and difference between current working condition temperature and normal temperature are obtained as follows:

[0068] Stress refers to the internal force per unit area of an object caused by external force, temperature change, or deformation constraint, and reflects the material's ability to resist deformation. Strain refers to the relative deformation of an object under stress, i.e., the ratio of deformation to original size.

[0069] Buried strain gauges (such as vibrating wire strain gauges) are placed on the surface or inside the support structure to directly measure strain values, and strain is calculated using Hooke's Law Stress is calculated using Hooke's Law , , The elastic modulus of the support.

[0070] The axial force value of the anchor rod refers to the internal force borne by the anchor rod along the axial direction, mainly tensile force, which is generated by the deformation of the surrounding rock and transmitted to the anchor rod.

[0071] A force gauge (such as a steel string force gauge) is installed at the tail of the anchor rod to directly measure the axial force value of the anchor rod.

[0072] The elastic modulus of the surrounding rock refers to the proportional constant of the stress value and strain value in the elastic deformation stage, and the elastic modulus reflects the rock mass's ability to resist elastic deformation.

[0073] The thermal expansion coefficient refers to the relative change in length or volume caused by unit temperature change when the material changes in temperature.

[0074] A temperature gradient is applied to the support material test piece (such as a concrete test block), the length change is measured, and the thermal expansion coefficient is calculated wherein, is the length change, is the initial length, is the difference between the current working condition temperature and the normal temperature.

[0075] The single cycle temperature change amplitude refers to the temperature fluctuation range (such as the difference between the maximum temperature and the minimum temperature) of the surrounding rock in a single inflation / deflation cycle of the energy storage cavern. Temperature sensors (such as thermocouples, thermal resistors) are arranged in the cavern to record the temperature change during the cycle and obtain the single cycle temperature change amplitude.

[0076] The single inflation / deflation cycle duration refers to the time required for the compressed air energy storage system to complete one "inflation energy storage-deflation energy release" process.

[0077] Obtain the cycle length data (e.g., 2 hours of inflation + 2 hours of deflation as a cycle, and the cycle length of inflation / deflation is 4 hours) directly from the energy storage system control platform.

[0078] The reference consolidation time at normal temperature refers to the time required for the rock mass to complete the main consolidation (the pore water pressure is basically dissipated) under a given stress condition at normal temperature.

[0079] Consolidation test: apply a constant load and measure the time required for the pore water pressure to dissipate to 90% as the reference consolidation time.

[0080] The temperature influence coefficient on the consolidation time refers to the degree of influence of temperature change on the consolidation time of the rock mass. Perform a consolidation test at different temperatures, fit the relationship curve between the consolidation time and the temperature, and the temperature influence coefficient on the consolidation time is the slope of the curve.

[0081] The difference between the current working temperature and the normal temperature (T ) is the current operating temperature of the energy storage cavern and the normal temperature.

[0082] The current temperature in the cavern is directly measured by a temperature sensor, and the difference is calculated by comparing it with the normal temperature.

[0083] On the basis of the above embodiments, the stress values, strain values, axial force values of the anchor rods, elastic modulus of surrounding rock, thermal expansion coefficient, temperature variation amplitude of single cycle, cycle length of single inflation / deflation, reference consolidation time at normal temperature, temperature influence coefficient on the consolidation time, and the difference between the current working temperature and the normal temperature are all mean-processed data.

[0084] On the basis of the above embodiments, after collecting the stress values, strain values, axial force values of the anchor rods, elastic modulus of surrounding rock, thermal expansion coefficient, temperature variation amplitude of single cycle, cycle length of single inflation / deflation, reference consolidation time at normal temperature, temperature influence coefficient on the consolidation time, and the difference between the current working temperature and the normal temperature, the above parameters are respectively subjected to maximum-minimum normalization processing, and then the normalized data is used for subsequent analysis and processing, so that various data can be analyzed and processed under the same dimension in the subsequent analysis and processing process, avoiding the problem that some data are ignored due to different dimensions.

[0085] On the basis of the above embodiments, the pre-trained adversarial network is extracted from the database, and the specific process is as follows:

[0086] Select an engineering scene model similar to the current task (such as a traditional underground cavern or a support stability model of a high-pressure gas storage) from the database to ensure that its input and output parameters match the energy storage cavern;

[0087] For example, if there is a "tunnel anchor support stability evaluation model" in the database, its input parameters include rock elastic modulus and thermal expansion coefficient, which can be used as a pre-trained model.

[0088] The pre-trained model usually contains two parts:

[0089] Generator: used to "manufacture" simulation parameters (such as generating possible stress values according to rock elastic modulus);

[0090] Discriminator: used to "discriminate" whether the data is real monitoring value or generated simulation value;

[0091] Directly extract the parameters of the two components (such as the weights and hierarchical structure of the neural network), without the need to rebuild the network framework;

[0092] Copy the parameters of the pre-trained model (such as the connection strength of each layer in the generator) directly to the current network, which is equivalent to "borrowing" the learning achievements of the existing model;

[0093] If the number of parameters for the current task is larger (such as adding "inflation / deflation cycle length" input), add corresponding input layer at the front of the model;

[0094] If the number of parameters is smaller, delete the irrelevant input layer in the pre-trained model (such as deleting the "seismic load" related input);

[0095] Input simple data: input the migrated network with a set of known reasonable parameters (such as rock elastic modulus = 20GPa), and check if the output is consistent with common sense (such as stress value should be positive, anchor rod axial force should be within the design range);

[0096] Calibrate the output range: ensure that the simulation parameters (such as stress and strain) generated by the generator are within the physically feasible range (such as stress should not exceed the compressive strength of the surrounding rock);

[0097] Normalize parameters with different units;

[0098] Divide the collected measured data into training set and validation set;

[0099] Generate simulated mechanical parameters (such as stress and anchor rod axial force) according to the input measured parameters (such as rock elastic modulus and inflation cycle length);

[0100] Determine whether the input data is "real monitoring data" or "generated simulation data", and feed it back to the generator;

[0101] The generator continuously adjusts the parameters to make the generated data "fool" the discriminator as much as possible;

[0102] The discriminator continuously improves its discrimination ability to distinguish between real data and simulation data;

[0103] When the generated data is basically consistent with the real data in statistical characteristics (such as mean and distribution shape), stop training.

[0104] Based on the above embodiment, extracting a pre-trained adversarial network from a database has the following advantages:

[0105] No need to train models from scratch; instead, you can leverage the learning results of pre-trained models in similar fields to shorten the R&D cycle.

[0106] To address the problem of insufficient measured data for energy storage caverns (e.g., missing data for extreme temperature-pressure combination conditions), the generator can "create" reasonable simulation data to fill the data gaps.

[0107] If new monitoring data is obtained later (such as new stress values ​​after the operation of the tunnel), the new data can be directly added to the training set to perform local fine-tuning on the model instead of retraining the entire network.

[0108] Based on the above embodiment, the pre-trained adversarial network is extracted from the database and the model parameters are transferred to the current adversarial network. The specific steps are as follows:

[0109] In the process of extracting pre-trained adversarial networks, a dynamic similarity matching algorithm is introduced to construct feature vectors based on the influencing parameters. Based on the feature vectors, the Euclidean distance between the influencing parameters of the pre-trained adversarial network and the current adversarial network is calculated. The similarity between the two is measured by the Euclidean distance. The smaller the distance, the higher the similarity. The pre-trained adversarial networks with the top three similarities are selected according to the similarity ranking.

[0110] The Euclidean distance between the influencing parameters of the pre-trained adversarial network and the current adversarial network is calculated based on the following formula:

[0111] ;

[0112] in, For the The Euclidean distance between the influencing parameters of the pre-trained adversarial network and the current adversarial network, that is, the similarity between the pre-trained adversarial network and the current adversarial network;

[0113] Where, For the The first Influencing parameters, The current adversarial network Influencing parameters, is the index of the pre-trained adversarial network, is the index of the influencing parameter, , correspond to the elastic modulus of the surrounding rock, the thermal expansion coefficient, the temperature variation amplitude of a single cycle, the length of a single inflation / deflation cycle, the reference consolidation time at normal temperature, the influence coefficient of temperature on the consolidation time, the difference between the current working temperature and the normal temperature, the thermal-mechanical coupling risk coefficient, and the seepage-stress lag coefficient, respectively;

[0114] The weighted fusion migration mode is adopted, a corresponding weight is given according to the similarity of each pre-trained adversarial network and the current adversarial network, and the parameters of multiple pre-trained adversarial networks are superimposed to the current adversarial network according to the weight;

[0115] The parameters of the pre-trained adversarial network are the weight matrix of the generator, the bias vector of the generator, the weight matrix of the discriminator, and the bias vector of the discriminator;

[0116] The top three pre-trained adversarial networks with the highest similarity are pre-trained adversarial network A, pre-trained adversarial network B, and pre-trained adversarial network C in turn, the weight coefficient of each pre-trained adversarial network is determined according to the similarity of each pre-trained adversarial network and the current adversarial network, and the higher the similarity, the greater the weight coefficient;

[0117] ;

[0118] wherein, is the i-th parameter of the current adversarial network, is the i-th parameter of the pre-trained adversarial network A, is the i-th parameter of the pre-trained adversarial network B, is the i-th parameter of the pre-trained adversarial network C, is the weight coefficient of the pre-trained adversarial network A, is the weight coefficient of the pre-trained adversarial network B, is the weight coefficient of the pre-trained adversarial network C, is the index of the pre-trained adversarial network parameter, , correspond to the weight matrix of the generator, the bias vector of the generator, the weight matrix of the discriminator, and the bias vector of the discriminator, respectively, and . on the basis of . .

[0119] Table 1. Thermal-mechanical coupling risk coefficient with elastic modulus, thermal expansion coefficient, temperature variation amplitude of a single cycle, and length of a single inflation / deflation cycle

[0120]

[0121] ​From Table 1, the elastic modulus gradually increases from 10 to 22, and the thermal-mechanical coupling risk coefficient continuously increases from 1.13 to 67.61, indicating that the greater the elastic modulus, the greater the stiffness of the structure under the action of heat and force, the more significant the stress accumulation effect, and the higher the risk of thermal-mechanical coupling. Therefore, the thermal-mechanical coupling risk coefficient is positively correlated with the elastic modulus;

[0122] The thermal expansion coefficient increases from 0.1 to 0.82, and the risk coefficient increases synchronously, indicating that the stronger the thermal expansion characteristics of the rock-soil body or structural material, the greater the thermal stress generated in the temperature cycle change, and the higher the coupling risk. Therefore, the thermal-mechanical coupling risk coefficient is positively correlated with the thermal expansion coefficient;

[0123] The single-cycle temperature change amplitude increases from 1℃ to 5.8℃, and the risk coefficient increases from 1.13 to 67.61, indicating that the greater the temperature fluctuation amplitude, the more intense the alternating thermal stress, the more significant the cyclic thermal load borne by the structure, and the higher the coupling risk. Therefore, the thermal-mechanical coupling risk coefficient is positively correlated with the single-cycle temperature change amplitude;

[0124] The single inflation / deflation cycle length is shortened from 8h to 0.6h, and the risk coefficient increases from 1.13 to 67.61, indicating that the shorter the cycle period, the higher the frequency of thermal-mechanical action, the more intensive the repeated load borne by the structure in a short period of time, the more obvious the cumulative effect of thermal-mechanical coupling, and the higher the risk. Therefore, the thermal-mechanical coupling risk coefficient is negatively correlated with the single inflation / deflation cycle length.

[0125] According to Figures 2-5 It can be seen that the thermal-mechanical coupling risk coefficient is positively correlated with the elastic modulus, the thermal expansion coefficient, and the single-cycle temperature change amplitude (and there is an accelerated growth section), and is negatively correlated with the single inflation / deflation cycle length (also with an accelerated decline section).

[0126] On the basis of the above embodiments, the thermal-mechanical coupling risk coefficient is calculated, and the formula is as follows:

[0127] ;

[0128] Among them, is the thermal-mechanical coupling risk coefficient, which is used to combine the elastic modulus, the thermal expansion coefficient, the single-cycle temperature change amplitude, and the single inflation / deflation cycle length to evaluate the thermal-mechanical coupling risk of the energy storage chamber, and the greater the thermal-mechanical coupling risk coefficient, the higher the thermal-mechanical coupling risk of the energy storage chamber;

[0129] In the formula, is the single-cycle temperature change amplitude, is the single inflation / deflation cycle length;

[0130] On this basis, it needs to be explained that:

[0131] When the elastic modulus increases, according to Hooke's law, the thermal stress generated inside the material during thermal expansion and contraction deformation caused by temperature change increases, and for high stiffness materials, it is difficult to release thermal stress through deformation, which leads to an increase in the risk of stress concentration, thus increasing the risk of thermal-mechanical coupling of the energy storage cavern, and thus increasing the risk coefficient of thermal-mechanical coupling.

[0132] When the thermal expansion coefficient increases, according to the formula of the thermal deformation of the material and the thermal expansion coefficient, the thermal deformation of the material increases, and greater deformation will cause greater thermal stress inside the structure, especially in the confined space of the cavern, and the deformation will exacerbate stress accumulation, which will increase the risk of thermal-mechanical coupling of the energy storage cavern, and thus increase the risk coefficient of thermal-mechanical coupling.

[0133] When the temperature change amplitude of a single cycle increases, the greater the temperature change, the more intense the material expansion / contraction, and intense temperature cycling will cause the material to repeatedly bear tensile and compressive stress, increasing the risk of fatigue damage, which will increase the risk of thermal-mechanical coupling of the energy storage cavern, and thus increase the risk coefficient of thermal-mechanical coupling.

[0134] When the single inflation / deflation cycle length increases, the temperature change rate decreases, and the heat cannot be conducted in time, resulting in a large temperature difference between the inside and outside of the cavern, generating a significant temperature gradient, causing additional thermal stress, in addition, the cycle frequency decreases, resulting in a decrease in the number of stress cycles per unit time, and fatigue damage is light, which will reduce the risk of thermal-mechanical coupling of the energy storage cavern, and thus reduce the risk coefficient of thermal-mechanical coupling.

[0135] Therefore, the risk coefficient of thermal-mechanical coupling and the elastic modulus, thermal expansion coefficient, and temperature change amplitude of a single cycle are positively correlated, and the risk coefficient of thermal-mechanical coupling and the single inflation / deflation cycle length are negatively correlated.

[0136] In addition, reflects the material's ability to resist elastic deformation, reflects the material's sensitivity to temperature changes, and the product of the two ( ) is the core term of thermal stress calculation (combination of Hooke's law and thermal expansion formula), which directly determines the basic thermal stress level caused by temperature change; Taking ( ) as the coefficient base, it shows that these two parameters are inherent properties of thermal-mechanical coupling risk and are directly related to the material itself.

[0137] characterizes the temperature fluctuation intensity of a single cycle, Reflects the cycle speed (the shorter the duration, the higher the frequency), the ratio of the two ( ) is essentially the temperature change rate (temperature fluctuation per unit time), which directly affects the uniformity of heat conduction and the frequency of fatigue damage; The dynamic correction of foundation thermal stress reflects the amplification or suppression of risk by the time effect of the cyclic process.

[0138] In summary, the above function form is used to express the functional relationship between the thermal-mechanical coupling risk coefficient and the elastic modulus, thermal expansion coefficient, temperature change amplitude of a single cycle, and duration of a single inflation / deflation cycle.

[0139] Based on the above embodiment, thermal-mechanical coupling will directly generate thermal stress. is the basic thermal stress term (similar to Hooke's law: stress = elastic modulus × strain, and strain is caused by temperature change); when When it increases, it indicates that the thermal stress risk is higher, that is, the thermal stress term is superimposed on the original mechanical stress.

[0140] The total strain is composed of mechanical strain and thermal strain. is positively correlated, in Reflects the sensitivity of the material to thermal deformation. Indirect assessment of contingency risk can be considered The larger it is, the greater the total strain (especially the contribution of thermal strain) is, and the higher the risk of structural deformation, that is, thermal strain is superimposed on mechanical strain.

[0141] The anchor rod bears the stress transfer of the support. When the thermal stress causes the structure to deform, the anchor rod will be subjected to additional force due to deformation coordination. For example, the structure is "pulled" by the anchor rod due to thermal expansion, and the axial force of the anchor rod may increase. The additional force caused by thermal stress needs to be considered in the original axial force calculation. Positive correlation.

[0142] It is a comprehensive indicator to measure the risk of thermal-mechanical coupling. The larger the value, the higher the risk of thermal stress, thermal strain and anchor additional force.

[0143] Table 2. Changes in the seepage-stress hysteresis coefficient with the baseline consolidation time at room temperature, the duration of a single inflation / deflation cycle, the influence coefficient of temperature on consolidation time, and the difference between the current working temperature and room temperature.

[0144]

[0145] As shown in Table 2, as the benchmark consolidation time gradually increases from 2 to 26, the seepage-stress hysteresis coefficient continues to increase from 0.05 to 0.78. This indicates that at room temperature, the longer the benchmark consolidation time is, the longer the basic period for the rock and soil to complete consolidation is. In the dynamic coupling process of seepage and stress, the cumulative hysteresis effect is more prominent, resulting in a larger seepage-stress hysteresis coefficient and a more significant coupling hysteresis characteristic. Therefore, the seepage-stress hysteresis coefficient and the benchmark consolidation time are positively correlated.

[0146] The duration of a single inflation / deflation cycle gradually shortened from 8 to 0.6, and the seepage-stress hysteresis coefficient continued to increase from 0.05 to 0.78. This indicates that the shorter the cycle duration, the higher the frequency of alternating changes in seepage and stress. The pore water discharge and stress adjustment inside the rock and soil cannot keep up with the cycle rhythm, and the hysteresis effect is enhanced, resulting in an increase in the seepage-stress hysteresis coefficient. Therefore, the seepage-stress hysteresis coefficient is negatively correlated with the duration of a single inflation / deflation cycle.

[0147] The influence coefficient of temperature on consolidation time gradually decreased from 0.25 to 0.01, and the seepage-stress hysteresis coefficient continued to increase from 0.05 to 0.78, which means that the weaker the influence of temperature on consolidation time (the smaller the influence coefficient), the less the actual consolidation process is affected by temperature and is relatively more stable. However, since this coefficient is negatively correlated with the hysteresis coefficient, as the coefficient decreases, the hysteresis coefficient increases instead, reflecting that there is an inverse correlation between the temperature effect and the seepage-stress hysteresis effect. When the temperature effect is weak, the hysteresis effect is more likely to appear due to the relatively stable consolidation environment. Therefore, the seepage-stress hysteresis coefficient and the influence coefficient of temperature on consolidation time are negatively correlated.

[0148] The difference between the current operating temperature and normal temperature gradually decreases from 5.8 to 1, and the seepage-stress hysteresis coefficient continues to increase from 0.05 to 0.78. This shows that the closer the operating temperature is to normal temperature, the less the temperature change interferes with the consolidation time and the seepage-stress coupling process, and the more obvious the hysteresis effect is, which increases the seepage-stress hysteresis coefficient. This reflects the reverse regulation of the temperature difference on the seepage-stress hysteresis characteristics. The smaller the temperature difference, the larger the hysteresis coefficient. Therefore, the seepage-stress hysteresis coefficient and the difference between the current operating temperature and normal temperature are negatively correlated.

[0149] according to Figures 6-9 It can be seen that the benchmark consolidation time is positively correlated with the hysteresis coefficient. As the benchmark consolidation time increases, the hysteresis coefficient increases, indicating that the longer the consolidation time, the more significant the seepage-stress response hysteresis.

[0150] The duration of a single inflation / deflation cycle is negatively correlated with the hysteresis coefficient. The shorter the cycle duration, the larger the hysteresis coefficient, indicating that short-cycle cycles will enhance the seepage-stress hysteresis effect.

[0151] The influence coefficient of temperature on consolidation time is negatively correlated with the hysteresis coefficient, the smaller the influence coefficient, the greater the hysteresis coefficient, and when the temperature interference is weak, the hysteresis characteristic is more prominent.

[0152] The difference value between the current working temperature and the normal temperature is negatively correlated with the hysteresis coefficient, the smaller the difference value, the greater the hysteresis coefficient, and when the temperature is stable, the hysteresis effect is more likely to appear.

[0153] On the basis of the above embodiments, the seepage-stress hysteresis coefficient is calculated, and the formula is as follows:

[0154] ;

[0155] Among them, The seepage-stress hysteresis coefficient is used to evaluate the dynamic coupling hysteresis characteristic of the seepage field and the stress field in the energy storage chamber by combining the reference consolidation time at normal temperature, the single inflation / deflation cycle time, the influence coefficient of temperature on consolidation time, and the difference value between the current working temperature and the normal temperature four index parameters, and the greater the seepage-stress hysteresis coefficient, the more significant the hysteresis effect of seepage and stress response, and the higher the coupling risk;

[0156] In the formula, is the reference consolidation time at normal temperature, is the influence coefficient of temperature on consolidation time, is the difference value between the current working temperature and the normal temperature;

[0157] On this basis, it needs to be explained that:

[0158] When the reference consolidation time at normal temperature increases, it indicates that the rock permeability is low or the pore water viscosity is high, and the pore water pressure dissipates slowly. In the inflation / deflation cycle of the energy storage chamber, the stress field change will precede the response of the seepage field, the stress change has occurred, but the seepage field cannot adjust in time due to slow consolidation, resulting in different dynamic responses of the two, the hysteresis effect of seepage and stress response increases, the coupling risk increases, and the seepage-stress hysteresis coefficient increases;

[0159] When the single inflation / deflation cycle time increases, the stress cycle frequency decreases (such as slow inflation / deflation), the stress change amplitude per unit time decreases, the seepage field has more time to respond to the stress change, the hysteresis effect of seepage and stress response decreases, the coupling risk decreases, and the seepage-stress hysteresis coefficient decreases;

[0160] When the influence coefficient of temperature on consolidation time increases, it indicates that when the temperature rises, the medium permeability improves more significantly, and the pore water pressure dissipates faster. Even if the difference value between the current working temperature and the normal temperature is the same, the greater The actual consolidation time will be further shortened, the seepage field can respond to the stress field change faster, the hysteresis effect of seepage and stress response is reduced, the coupling risk is reduced, and the seepage-stress hysteresis coefficient is reduced;

[0161] When the difference between the current working temperature and the normal temperature increases, the viscosity coefficient of water decreases, and the thermal expansion of the rock mass may open microcracks, both of which will increase the permeability, shorten the consolidation time, and make the seepage field respond to the stress field faster, reduce the hysteresis effect of seepage and stress response, reduce the coupling risk, and reduce the seepage-stress hysteresis coefficient.

[0162] Therefore, the seepage-stress hysteresis coefficient and the reference consolidation time at normal temperature are positively correlated, and the seepage-stress hysteresis coefficient and the single inflation / deflation cycle length, the temperature influence coefficient on the consolidation time, and the difference between the current working temperature and the normal temperature are negatively correlated.

[0163] In addition, (T ) is the ratio of the reference consolidation time to the cycle length, which is used to quantify the relative relationship between the “natural response speed of the seepage field” and the “change speed of the stress field”:

[0164] When , the response speed of the seepage field is much slower than the change speed of the stress field, resulting in significant hysteresis effect;

[0165] When , the seepage field has enough time to respond to the stress change, resulting in weak hysteresis effect;

[0166] As a magnification / reduction factor of temperature influence:

[0167] When the temperature rises ( ), makes the system coefficient decrease, which reflects the weakening effect of temperature on the hysteresis effect, and together with ( ) determines the final hysteresis degree;

[0168] When the temperature rises ( ), makes the system coefficient increase, which reflects the strengthening effect of temperature on the hysteresis effect, and is superimposed with ( );

[0169] Therefore, (T ) is the core proportion item of the formula, which establishes the reference level of the hysteresis effect by comparing the “seepage field consolidation speed” and the “stress field cycle speed”, on this basis, the hysteresis degree is further adjusted through the influence of temperature on permeability, and finally a comprehensive evaluation of the seepage-stress coupling hysteresis characteristics is formed.

[0170] In summary, the function form is used to express the function relationship between the seepage-stress hysteresis coefficient and the reference consolidation time at normal temperature, the single inflation / deflation cycle time, the temperature influence coefficient on the consolidation time, and the difference between the current working temperature and the normal temperature.

[0171] On the basis of the above embodiment, the seepage field response hysteresis will cause the pore water pressure to be unable to dissipate in time. According to the Terzaghi effective stress principle, if the pore water pressure dissipates hysteresis, the change of the effective stress will lag behind the total stress, thereby affecting the mechanical behavior (such as strain and anchor force) of the rock mass; the hysteresis effect can cause additional stress concentration or deformation difference in the rock mass, which needs to be corrected by correcting the traditional mechanical calculation results.

[0172] The seepage-stress hysteresis coefficient (C) ) indirectly changes the effective stress and rock mass deformation by affecting the pore water pressure dissipation speed, thereby correcting the stress, strain, and anchor shaft force in the traditional thermal-mechanical coupling calculation. The core idea is to as a quantitative index of the hysteresis effect, is added to the original mechanical calculation results through a linear or nonlinear coefficient (such as ) to reflect the additional risk caused by the asynchronization of seepage and stress field.

[0173] S2. Construct a thermal-fluid-solid coupling finite element simulation model based on the mechanical parameters and influence parameters of the support sample, and calibrate the simulation model based on the simulated mechanical parameters and the corresponding simulated influence parameters;

[0174] On the basis of the above embodiment, a thermal-fluid-solid coupling finite element simulation model is constructed based on the mechanical parameters and the measured influence parameters of the support sample, and the specific process is as follows:

[0175] Prepare data and determine the data requirements of the model range: mechanical parameters: stress value, strain value, and anchor shaft force value; influence parameters: surrounding rock elastic modulus, thermal expansion coefficient, inflation / deflation cycle time, and consolidation time;

[0176] Model range: take the chamber as the center and take the rock mass with a diameter of 3 times the chamber diameter;

[0177] Grid division and material definition: grid division: dense grid around the chamber, coarse grid in the far field; support structure (anchor) uses one-dimensional rod element, and rock mass uses two-dimensional plane element; material definition: rock mass: assign elastic modulus, thermal expansion coefficient, and permeability coefficient; anchor: elastic material, only bears tensile and compressive load;

[0178] Apply boundary conditions: thermal-mechanical boundary: chamber inner wall: cyclic temperature load; rock mass far away: fixed temperature;

[0179] Seepage boundary: rock mass bottom: fixed value of pore water pressure; chamber wall: zero seepage flux (assuming that the supporting structure is waterproof); mechanical boundary: initial ground stress: calculated according to the weight of the rock mass; chamber: cyclic gas pressure load (simulating inflation / deflation);

[0180] Set up multi-field coupling relationship: thermal-mechanical coupling: thermal expansion of rock mass caused by temperature change, resulting in thermal stress;

[0181] Seepage-mechanical coupling: pore water pressure affects rock mass stress through effective stress principle;

[0182] Run the model and analyze the results: first calculate the temperature field to get the temperature distribution at each point; calculate the thermal stress and rock mass deformation by taking the temperature field as input; finally calculate the seepage field and analyze the pore water pressure distribution.

[0183] On the basis of the above embodiment, the simulation model is calibrated based on the simulated mechanical parameters and their corresponding simulated influence parameters, the specific process being as follows:

[0184] Simulation data preprocessing and feature extraction

[0185] Parameter initialization: according to the mechanical parameters (stress value, strain value, and axial force value of anchor rod) and influence parameters (elastic modulus of surrounding rock, thermal expansion coefficient, inflation / deflation cycle length, and consolidation time) of the supporting sample, the material properties and boundary conditions in the finite element model are initialized and set;

[0186] Run the simulation model: use the initialized parameters to run the thermal-flow-solid coupling model, simulate the multi-field response of the energy storage chamber during inflation / deflation cycle, and obtain the mechanical parameters output by the model, including stress value, strain value, and axial force value of anchor rod;

[0187] Compare the simulated and actual parameters: compare the simulated mechanical parameters output by the model with the simulated mechanical parameters obtained through the trained adversarial network and their corresponding simulated influence parameters, and analyze the differences between them;

[0188] Adjust the model parameters: according to the comparison results, use optimization algorithms or manual adjustment methods to adjust the parameters in the finite element simulation model, for example, when the simulated stress value is inconsistent with the actual simulated parameter, the rock mass damping coefficient can be increased or the elastic modulus can be reduced;

[0189] Iterative optimization: repeat the steps of comparing the simulated and actual parameters and adjusting the model parameters, and continuously adjust the model parameters until the difference between the simulated mechanical parameters output by the model and the given simulated parameters reaches an acceptable range, completing the calibration of the finite element simulation model.

[0190] S3. Input the influence parameters of the support to be judged into the calibrated simulation model to obtain the mechanical parameters of the support to be judged.

[0191] S4. Extract characteristic parameters from the mechanical parameters of the support to be identified, and obtain the maximum stress value, the maximum strain value, and the maximum axial force value of the anchor;

[0192] Based on the above embodiment, the maximum stress value, the maximum strain value and the maximum axial force value of the anchor rod are obtained according to the following formula:

[0193] The support was obtained through the finite element simulation model The stress value of each measuring point, , calculate the maximum stress value of the support:

[0194] ;

[0195] in, is the maximum stress value of the support, For the support The stress value of each measuring point, is the index of the measurement point, is the number of support measurement points;

[0196] The support was obtained through the finite element simulation model The strain value of each measuring point, , calculate the maximum strain value of the support:

[0197] ;

[0198] in, is the maximum strain value of the support, For the support The strain value of each measuring point;

[0199] The finite element simulation model The axial force of the root anchor, ; Calculate the maximum axial force of the anchor rod:

[0200] ;

[0201] in, is the maximum axial force of the anchor rod, For the The axial force value of the anchor rod, is the index of the anchor, , is the number of anchor rods.

[0202] S5. Process the maximum stress, maximum strain, and maximum axial force of the support to be identified, respectively, to generate a stress safety factor, a strain safety factor, and an anchor axial force safety factor for the support to be identified;

[0203] On the basis of the above embodiment, the stability coefficient of the support to be judged is obtained, and the formula is as follows:

[0204] ;

[0205] ;

[0206] ;

[0207] ;

[0208] wherein, is the stability coefficient of the support to be judged, the stability coefficient is used to take the minimum value from the stress safety factor, the strain safety factor and the anchor rod axial force safety factor to evaluate the stability of the support to be judged, and the greater the stability coefficient, the higher the stability of the support to be judged;

[0209] In the formula, is the stress safety factor, is the strain safety factor, is the anchor rod axial force safety factor, is the maximum stress that the support can withstand, is the maximum strain that the support can withstand, is the maximum axial force allowed when the anchor rod is designed.

[0210] S6. According to the stress safety factor, the strain safety factor and the anchor rod axial force safety factor of the support to be judged, the stability state of the support to be judged is evaluated.

[0211] On the basis of the above embodiment, the specific process of step S6 is as follows:

[0212] The stability of the support is determined by the minimum value of the stress safety factor , the strain safety factor and the anchor rod axial force safety factor When any index does not meet the safety requirement, the support will be unstable;

[0213] When , it means that all three safety factors are greater than 1, then the ultimate bearing capacity of the support is greater than the actual load, and the support is stable;

[0214] When , it means that at least one of the three safety factors is equal to 1, then the actual load of the support reaches the ultimate bearing capacity, and the support is close to failure;

[0215] When , it means that at least one of the three safety factors is less than 1, then the actual load of the support exceeds the ultimate bearing capacity, and the support is unstable.

[0216] Wherein, "1" is the mathematical representation of the limit capacity equal to the actual load, and is the demarcation point between stability and instability.

[0217] The above formulas are dimensionless values calculated, and the formulas are obtained by software simulation of a large number of collected data to obtain a formula of the most recent real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0218] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0219] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0220] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A compressed air energy storage cavern support stability discrimination method, characterized in that: The specific steps include: S1. Collect the support samples of the cavern and the mechanical parameters and influence parameters of the support to be judged, construct a current adversarial network for the mechanical parameters and influence parameters of the cavern, extract a pre-trained adversarial network from a database, migrate model parameters to the current adversarial network, complete parameter initialization of the current adversarial network, train the current adversarial network using the mechanical parameters and influence parameters to obtain simulated mechanical parameters and corresponding simulated influence parameters, and the influence parameters include the elastic modulus of surrounding rock, the thermal expansion coefficient, the temperature variation amplitude of a single cycle, the single inflation / deflation cycle duration, the reference consolidation time at normal temperature, the influence coefficient of temperature on consolidation time, the difference between the current working condition temperature and the normal temperature, and the thermal-mechanical coupling risk coefficient and the seepage-stress hysteresis coefficient obtained based on the above parameters; S2. Construct a thermal-flow-solid coupling finite element simulation model based on the mechanical parameters and influence parameters of the support samples, and calibrate the simulation model based on the simulated mechanical parameters and corresponding simulated influence parameters; S3. Input the influence parameters of the support to be judged into the calibrated simulation model to obtain the mechanical parameters of the support to be judged; S4. Extract feature parameters from the mechanical parameters of the support to be judged to obtain the maximum stress value, the maximum strain value, and the maximum axial force value of the anchor rod; S5. Perform data processing on the maximum stress, maximum strain, and maximum axial force value of the anchor rod of the support to be judged respectively to generate the stress safety factor, strain safety factor, and anchor rod axial force safety factor of the support to be judged; S6. Evaluate the stability state of the support to be judged according to the stress safety factor, strain safety factor, and anchor rod axial force safety factor of the support to be judged.

2. The compressed air energy storage cavern support stability discrimination method of claim 1, wherein: The mechanical parameters include stress value, strain value, and axial force value of the anchor rod.

3. The compressed air energy storage cavern support stability discrimination method of claim 1, wherein: The specific steps of extracting the pre-trained adversarial network from the database and migrating the model parameters to the current adversarial network are as follows: In the process of extracting the pre-trained adversarial network, a dynamic similarity matching algorithm is introduced, a feature vector is constructed based on the influence parameters, and the Euclidean distance between the influence parameters of the pre-trained adversarial network and the current adversarial network is calculated based on the feature vector to select the pre-trained adversarial networks with the top 3 similarities; Wherein, the formula for calculating the Euclidean distance between the influence parameters of the pre-trained adversarial network and the current adversarial network is as follows: ； wherein, is the Euclidean distance between the pre-trained adversarial network and the influence parameter of the current adversarial network, i.e., the similarity between the pre-trained adversarial network and the current adversarial network; is the Euclidean distance between the pre-trained adversarial network and the influence parameter of the current adversarial network, i.e., the similarity between the pre-trained adversarial network and the current adversarial network; In the formula, is the first influence parameter of the i-th pre-trained adversarial network, is the first influence parameter of the current adversarial network, is the index of the pre-trained adversarial network, is the index of the influence parameter, , respectively correspond to the elastic modulus of the surrounding rock, the thermal expansion coefficient, the temperature change amplitude of a single cycle, the length of a single inflation / deflation cycle, the reference consolidation time at normal temperature, the influence coefficient of temperature on the consolidation time, the difference between the current working temperature and the normal temperature, the thermal-mechanical coupling risk coefficient and the seepage-stress lag coefficient.​​​ A weighted fusion migration method is adopted, and each pre-trained adversarial network and the current adversarial network is assigned a corresponding weight according to the similarity, and the parameters of multiple pre-trained adversarial networks are superimposed and migrated to the current adversarial network according to the weight; The parameters of the pre-trained adversarial network are the weight matrix of the generator, the bias vector of the generator, the weight matrix of the discriminator, and the bias vector of the discriminator; The pre-trained adversarial networks with the top 3 similarities are pre-trained adversarial network A, pre-trained adversarial network B, and pre-trained adversarial network C, respectively, and the weight coefficients of each pre-trained adversarial network and the current adversarial network are determined according to the similarity, and the higher the similarity, the greater the weight coefficient; ； in, The current adversarial network parameters, is the 𝛿th parameter of the pre-trained adversarial network A, For the pre-trained adversarial network B parameters, is the first parameters, is the weight coefficient of the pre-trained adversarial network A, is the weight coefficient of the pre-trained adversarial network B, is the weight coefficient of the pre-trained adversarial network C, is the index of the pre-trained adversarial network parameters, , Corresponding to the weight matrix of the generator, the bias vector of the generator, the weight matrix of the discriminator and the bias vector of the discriminator, respectively, On the basis of .

4. The compressed air energy storage cavern support stability discrimination method of claim 1, wherein: The formula for calculating the thermal-mechanical coupling risk coefficient is as follows: ； wherein, is the thermal-mechanical coupling risk factor; wherein E is the modulus of elasticity of the support, CTE is the coefficient of thermal expansion, ΔΤ is the temperature variation amplitude per cycle, T is the duration of the single inflation / deflation cycle.

5. The compressed air energy storage cavern support stability discrimination method of claim 2, wherein: The formula for calculating the seepage-stress hysteresis coefficient is as follows: ； wherein, is the seepage-stress hysteresis coefficient; In the formula, is the reference consolidation time at normal temperature, is the temperature influence coefficient on the consolidation time, is the difference between the current working temperature and the normal temperature.

6. The compressed air energy storage cavern support stability discrimination method of claim 5, wherein: The formula for obtaining the stability coefficient of the support to be judged is as follows: ； ； ； ； wherein, K is the stability factor of the support to be judged; wherein, is the stress safety factor, is the strain safety factor, is the anchor rod axial force safety factor, is the maximum stress that the support can withstand, is the maximum strain that the support can withstand, is the maximum axial force allowed when designing the anchor rod, is the maximum stress value of the support, is the maximum strain value of the support, is the maximum axial force value of the anchor rod.

7. The compressed air energy storage cavern support stability discrimination method of claim 6, wherein: The specific process of step S6 is as follows: The stability of the support is determined by the minimum value of stress safety factor , strain safety factor , and anchor rod axial force safety factor , and any index not meeting the safety requirement will result in unstable support. When all three safety factors are greater than 1, the ultimate bearing capacity of the support is greater than the actual load, and the support is stable. When at least one of the three safety factors is equal to 1, the actual load of the support reaches the ultimate bearing capacity, and the support is on the verge of failure. When at least one of the three safety factors is less than 1, the actual load of the support exceeds the ultimate bearing capacity, and the support is unstable. Where "1" is the mathematical representation of the limit capacity equal to the actual load, and is the demarcation point between stability and instability.

Images