Dynamic test analysis method and system for rock mechanical strength and medium

Abstract

The invention discloses a dynamic test analysis method and system for rock mechanical strength and a medium, and relates to the technical field of rock performance test. The method comprises the following steps: building a rock testing system which comprises a sample preparation unit, an intelligent loading unit, a data acquisition unit and a data processing unit; preparing a rock sample according to a standard, and analyzing a test scheme; an intelligent loading unit is adopted to load a test according to the scheme, and meanwhile, a mechanical data flow and a deformation data flow are monitored through a data acquisition unit; calling a rock mechanical strength adaptive evaluation network based on the data processing unit; and performing intensity evaluation on the data stream to obtain an intensity analysis result. The invention relates to a rock mechanical strength self-adaptive evaluation network, and aims to solve the technical problem that the existing rock mechanical strength test method cannot accurately evaluate the rock mechanical properties in real time due to low test precision and data acquisition lagging. The technical effect of improving the accuracy and evaluation efficiency of the rock mechanical strength test is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of rock property testing, and specifically relates to a dynamic test analysis method, system and medium for rock mechanical strength. Background Art

[0002] Currently, the testing of rock mechanical strength mainly relies on traditional static loading and laboratory testing methods. However, these methods have certain limitations in practical applications. For example, they cannot reflect the mechanical response of rocks in a dynamic environment in real time, and there may be large errors and uncertainties due to human factors during the testing process. Therefore, how to accurately and real-time evaluate the rock mechanical strength, especially under complex dynamic loading conditions, has become an important issue in rock mechanics research and engineering applications. Most of the existing technologies rely on single experimental data analysis and standardized testing processes, lacking intelligent evaluation and real-time analysis means for different types of rocks under different testing conditions. In addition, traditional methods cannot make full use of historical data and actual rock property information for efficient mechanical evaluation, resulting in low efficiency of the testing process and the accuracy of the test results being affected by many factors.

[0003] To solve these problems, the present invention proposes a dynamic test analysis method for rock mechanical strength based on intelligent loading, data acquisition and adaptive evaluation network, aiming to achieve precise evaluation of rock mechanical properties and improve the accuracy and efficiency of testing by integrating modern data processing technologies and deep learning algorithms. Summary of the Invention

[0004] This application provides a dynamic test analysis method, system and medium for rock mechanical strength, which solves the technical problem that the existing rock mechanical strength testing methods cannot evaluate the rock mechanical properties in real time and accurately due to low testing accuracy and lagging data acquisition.

[0005] In the first aspect of this application, a dynamic test analysis method for rock mechanical strength is provided. The method includes: building a rock test system, which includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit and a data processing unit; preparing a rock specimen through the specimen preparation unit according to the rock test standard, and analyzing the test plan for the rock specimen to obtain a rock dynamic test plan; using the intelligent loading unit to load and test the rock specimen according to the rock dynamic test plan, and simultaneously monitoring the rock mechanical data stream and deformation data stream during the test process through the data acquisition unit; calling the rock mechanical strength adaptive evaluation network based on the data processing unit; and performing strength evaluation on the rock mechanical data stream and deformation data stream based on the rock mechanical strength adaptive evaluation network to obtain the rock mechanical strength analysis result.

[0006] In the second aspect of the present application, a dynamic test analysis system for rock mechanical strength is provided. The system includes: a test system construction component for constructing a rock test system, which includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit; a test plan analysis component for preparing a rock specimen through the specimen preparation unit according to the rock test standard and analyzing the test plan for the rock specimen to obtain a rock dynamic test plan; a loading test component for using the intelligent loading unit to perform a loading test on the rock specimen according to the rock dynamic test plan, and simultaneously monitoring the rock mechanical data stream and deformation data stream during the test process through the data acquisition unit; an evaluation network call component for calling an adaptive evaluation network for rock mechanical strength based on the data processing unit; and a strength evaluation component for performing strength evaluation on the rock mechanical data stream and deformation data stream based on the adaptive evaluation network for rock mechanical strength to obtain a rock mechanical strength analysis result.

[0007] In the third aspect of the present application, a computer-readable medium is provided, storing a computer program, which when executed by a processor, implements the dynamic test analysis method for rock mechanical strength provided by the present application.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] First, construct a rock test system, which includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit; subsequently, prepare a rock specimen through the specimen preparation unit according to the rock test standard and analyze the test plan for the rock specimen to obtain a rock dynamic test plan; further, use the intelligent loading unit to perform a loading test on the rock specimen according to the rock dynamic test plan, and simultaneously monitor the rock mechanical data stream and deformation data stream during the test process through the data acquisition unit; then, call an adaptive evaluation network for rock mechanical strength based on the data processing unit; finally, perform strength evaluation on the rock mechanical data stream and deformation data stream based on the adaptive evaluation network for rock mechanical strength to obtain a rock mechanical strength analysis result. This solves the technical problem that the existing rock mechanical strength test method cannot evaluate the rock mechanical properties in real time and accurately due to low test accuracy and lagging data acquisition. By constructing an intelligent rock test system and combining it with an adaptive evaluation network for rock mechanical strength, the technical effect of improving the accuracy and evaluation efficiency of rock mechanical strength testing is achieved. Description of the Drawings

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0011] Figure 1 Schematic flow chart of the dynamic test analysis method for rock mechanical strength provided by the embodiments of the present application;

[0012] Figure 2 Schematic structural diagram of the dynamic test analysis system for rock mechanical strength provided by the embodiments of the present application.

[0013] Explanation of reference numerals: Test system construction component 11, test scheme analysis component 12, loading test component 13, evaluation network call component 14, strength evaluation component 15. Detailed implementation manners

[0014] By providing a dynamic test analysis method, system and medium for rock mechanical strength, the present application solves the technical problem that the existing rock mechanical strength test methods cannot evaluate the rock mechanical properties in real time and accurately due to low test accuracy and lag in data acquisition. By building an intelligent rock test system and combining it with an adaptive evaluation network for rock mechanical strength, the technical effect of improving the accuracy and evaluation efficiency of rock mechanical strength tests is achieved.

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0016] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0017] Embodiment 1, as Figure 1 shown, the present application provides a dynamic test analysis method for rock mechanical strength, wherein the method includes:

[0018] Build a rock test system, and the rock test system includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit.

[0019] In one embodiment, the setup of the rock testing system is a comprehensive project, including multiple core units, namely the specimen preparation unit, the intelligent loading unit, the data acquisition unit, and the data processing unit. The rock testing system aims to achieve comprehensive and accurate testing of the mechanical properties of rocks through these core units. The specimen preparation unit is responsible for preparing standard rock specimens according to the geological characteristics of the rocks and the testing requirements. This process includes sampling, cutting, processing, and treating the rocks to ensure that the geometric shape and surface quality of the specimens meet the testing requirements. The intelligent loading unit is the core part of the system. It can apply dynamic or static loads to the rock specimens according to the preset testing scheme. This unit is usually equipped with high-precision hydraulic or electric loading devices that can precisely control the loading rate, load magnitude, and action time to simulate the stress conditions in real engineering environments. During the loading process, the data acquisition unit monitors and records the mechanical response data of the rock specimens in real time, including stress, strain, displacement, acoustic emission signals, etc. This unit is usually composed of high-sensitivity sensors, high-speed data acquisition cards, and signal conditioning equipment to ensure the accuracy and real-time nature of the data. The data processing unit is responsible for storing, analyzing, and processing the massive amounts of data collected. By invoking the rock mechanics strength adaptive evaluation network, this unit can deeply analyze the dynamic mechanical behavior of the rocks, generate mechanical strength analysis results, and provide a scientific basis for engineering applications. The entire system realizes the intelligentization and precision of rock mechanical property testing through the efficient cooperation of each unit.

[0020] A rock specimen is prepared through the specimen preparation unit in accordance with the rock testing standard, and the testing scheme for the rock specimen is analyzed to obtain a rock dynamic testing scheme.

[0021] In one embodiment, according to the rock testing standard, the specimen preparation unit first determines the preparation type and specifications of the specimen based on the geological conditions and mechanical strength testing objectives of the target rock. For example, for layered rocks, the influence of bedding direction on mechanical properties needs to be considered, so as to select a reasonable sampling position and cutting direction. During the preparation process, professional rock cutting machines, grinding machines and measuring tools are used to ensure that the dimensional accuracy and surface flatness of the specimen meet the standard requirements. After the preparation is completed, the specimen also needs to be numbered and recorded for subsequent testing and analysis. Subsequently, based on the prepared rock specimen, a test plan analysis is carried out. This process requires first clarifying the specific objectives of the mechanical strength test, such as compressive strength, tensile strength or shear strength, etc., and extracting key test indicators from them. Then, combined with the attribute information of the target rock (such as lithology, porosity, water content, etc.) and the historical test database, a suitable test plan is preliminarily determined through data mining and correlation matching. In order to further optimize the plan, numerical simulation technology is usually used to conduct virtual loading tests on the rock specimen to evaluate the influence of different test parameters (such as loading rate, load type) on the test results. According to the simulation results, the test plan is dynamically adjusted and optimized to finally obtain a scientific and reasonable rock dynamic test plan, providing guidance for subsequent actual loading tests.

[0022] Furthermore, the preparation of the rock specimen obtained by the specimen preparation unit according to the rock testing standard includes:

[0023] Obtaining the mechanical strength testing objective and rock geological conditions of the target rock; performing specimen analysis on the mechanical strength testing objective according to the rock testing standard to determine the specimen preparation type and specimen preparation specifications; performing sampling analysis on the rock geological conditions according to the rock testing standard to determine the rock sampling position; calling a rock sampling device through the specimen preparation unit to prepare a specimen for the target rock according to the specimen preparation type and specimen preparation specifications and the rock sampling position to obtain the rock specimen.

[0024] Preferably, determine the target of the mechanical strength of the rock to be tested according to the test requirements, such as mechanical property indexes such as compressive strength, tensile strength, and shear strength. At the same time, obtain the geological conditions of the target rock, including lithology, bedding structure, fracture development degree, mineral composition, porosity, and moisture content. These information provide important bases for subsequent specimen preparation. Subsequently, analyze the specimen for the mechanical strength test target according to the rock test standard, that is, determine the preparation type (such as cylindrical, cubic, or prismatic) and specifications (such as diameter, height, or side length) of the specimen according to the different test targets. For example, cylindrical specimens are usually used for compressive strength tests, while prismatic specimens may be required for tensile strength tests. At the same time, combined with the geological conditions of the rock, further determine the size range and precision requirements of the specimen to ensure the reliability and comparability of the test results. After that, conduct sampling analysis on the geological conditions of the rock based on the rock test standard to determine the rock sampling location. This process needs to consider the heterogeneity and anisotropy characteristics of the rock. For example, for layered rocks, the sampling location needs to be selected according to the bedding direction to reflect the actual mechanical behavior of the rock; for rocks with developed fractures, obvious fracture areas need to be avoided to ensure the integrity of the specimen. The selection of the sampling location also needs to be combined with the actual engineering requirements to ensure that the specimen can represent the overall characteristics of the target rock. Finally, call the rock sampling equipment through the specimen preparation unit and prepare the specimen according to the determined specimen preparation type, specifications, and sampling location. In this process, equipment such as rock drills, cutters, and grinders will be used to extract the initial sample from the target rock and perform precise processing according to the standard size. During the preparation process, the geometric precision and surface quality of the specimen need to be strictly controlled to avoid affecting the test results due to processing errors. After the preparation is completed, number, record, and store the specimen to ensure that it can be used for subsequent mechanical strength tests. This process finally obtains rock specimens that meet the standard requirements, providing a reliable basis for subsequent tests.

[0025] Furthermore, the obtaining of the rock dynamic test plan includes:

[0026] Obtain the mechanical strength test target of the rock specimen, extract the indexes of the mechanical strength test target to obtain a mechanical strength test index set; mine historical test data based on the mechanical strength test index set to obtain a rock mechanical strength index test database; perform association matching based on the attribute information of the target rock and the rock mechanical strength index test database to obtain a rock dynamic test plan.

[0027] Optionally, first, obtaining the mechanical strength test objectives of rock specimens is a key step in formulating the test plan. According to engineering requirements or research purposes, clarify the mechanical property indexes to be evaluated, such as compressive strength, tensile strength, shear strength, etc. These objectives reflect the mechanical behavior of rocks under different stress conditions and are the core basis for the subsequent test plan design. By extracting indexes from the mechanical strength test objectives, decompose them into specific and quantifiable test indexes to form a mechanical strength test index set. For example, the compressive strength test may include indexes such as peak strength, residual strength, and stress-strain curve. Subsequently, based on the mechanical strength test index set, conduct historical test data mining. By consulting literature, accessing laboratory databases, or using industry standard databases, collect historical test data of rock lithologies similar to the target rock. These historical data contain test results of a large number of different rock samples under similar conditions, so they can provide valuable references for the mechanical strength evaluation of the target rock. By sorting, cleaning, and classifying these data, construct a rock mechanical strength index test database, which provides data support and reference basis for the formulation of subsequent test plans. Then, based on the attribute information of the target rock (such as lithology, bedding direction, porosity, water content, etc.) and the rock mechanical strength index test database, conduct correlation matching. Through data analysis and pattern recognition techniques, screen out historical test cases similar to the attributes of the target rock, extract their test parameters and results, and then combine the specific characteristics of the target rock to optimize and adjust the historical test plan. For example, adjust the loading rate, loading method, or test environmental conditions to meet the actual needs of the target rock. Finally, generate a rock dynamic test plan suitable for the target rock, which can scientifically guide the subsequent mechanical strength test and ensure the accuracy and reliability of the test results. This process realizes the personalization and precision of the test plan in a data-driven manner, ensuring the accuracy and reliability of the test results.

[0028] Furthermore, the obtaining of the rock dynamic test plan includes:

[0029] Based on the attribute information of the target rock and the rock mechanical strength index test database, conduct correlation matching to determine the matching rock test plan; conduct a mechanical strength simulation test on the target rock according to the matching rock test plan to obtain the mechanical strength simulation test effect; based on the mechanical strength simulation test effect, adjust and optimize the matching rock test plan to obtain the rock dynamic test plan.

[0030] Optionally, based on the attribute information of the target rock (such as lithology, bedding direction, porosity, water content, etc.) and the rock mechanics strength index test database, perform correlation matching. Process the non-numerical items in the attribute information of the target rock and the test rock attribute information in the rock mechanics strength index test database through one-hot encoding, and then splice the processed data with the remaining numerical item data of each to obtain the attribute vectors of the target rock and the test rocks. Subsequently, calculate the similarity between the attribute vectors of the target rock and all test rocks through the cosine similarity calculation formula to obtain multiple similarity values. Perform a maximum value process on these similarity values, and obtain the corresponding historical test data from the rock mechanics strength index test database through the processing structure to understand parameters such as the loading method, loading rate, specimen size, and test environment, so as to determine a matching rock test plan. Then, according to the matching rock test plan, use numerical simulation technology to perform a mechanical strength simulation test on the target rock. By establishing a numerical model of the rock specimen (such as a finite element model or a discrete element model), simulate the mechanical response under actual loading conditions. During the simulation process, input the parameters in the matching test plan, such as the loading rate, load type, and environmental conditions, run the simulation and record data such as the stress-strain curve, displacement field distribution, and crack propagation pattern of the rock specimen to obtain the mechanical strength simulation test effect. For example, the simulation results may show that the stress concentration phenomenon of the rock specimen is obvious at certain loading rates, or the deformation mode of the specimen under certain boundary conditions does not conform to the actual situation. Finally, based on the mechanical strength simulation test effect, adjust and optimize the matching rock test plan. By comparing the simulation results with the expected target, identify the deficiencies or deviations in the test plan. For example, if the simulation results show that the specimen fails prematurely due to too fast a loading rate, then adjust the loading rate; if the boundary conditions are set unreasonably resulting in abnormal stress distribution, then optimize the boundary conditions. Through multiple iterations of simulation and parameter adjustment, gradually optimize the test plan to ensure that it can accurately reflect the mechanical behavior of the target rock. Finally, obtain a scientific and reasonable rock dynamic test plan, which can provide accurate guidance for actual loading tests and improve the reliability and engineering applicability of test results. This process combines simulation and optimization to achieve the dynamic adjustment and precise design of the test plan.

[0031] Furthermore, the obtaining of the rock dynamic test plan includes:

[0032] Based on the mechanical strength simulation test effect, perform adjustment analysis on the matching rock test plan to determine the plan optimization direction; according to the plan optimization direction, adjust and optimize the matching rock test plan to determine the rock dynamic test plan.

[0033] Optionally, conduct a detailed analysis of the results of the mechanical strength simulation test, and extract key data, such as stress-strain curves, displacement field distributions, crack propagation patterns, and failure modes, etc. By comparing the simulation results with the expected goals, identify the deficiencies or deviations in the test plan. For example, if the simulation results show that the specimen fails prematurely during loading, it may be that the loading rate is too fast or the boundary conditions are set unreasonably; if the stress distribution is uneven, it may be that the specimen size or loading method needs to be adjusted. By analyzing the simulation effect, clarify the specific problems that need to be optimized in the test plan, such as loading rate, loading mode, specimen size, or data acquisition frequency, etc. The core of this step is to find the weak links in the test plan through data-driven analysis, providing a basis for subsequent optimization. Subsequently, according to the analysis results of the simulation test effect, determine the optimization direction. For example, if the simulation results show that the specimen failure mode is abnormal due to too fast loading rate, the optimization direction is to reduce the loading rate; if the stress concentration phenomenon is obvious, the optimization direction is to adjust the specimen size or improve the contact method of the loading head; if the key mechanical behaviors are lost due to insufficient data acquisition frequency, the optimization direction is to increase the data acquisition frequency. After determining the optimization direction, adjust and optimize the matching rock test plan according to the determined optimization direction. For example, according to the simulation results, adjust the loading rate from high speed to medium speed or low speed to better capture the mechanical response of the rock; adjust the diameter or height of the specimen according to the stress distribution to reduce the influence of boundary effects; change from uniaxial compression to triaxial compression to simulate a more complex stress state; optimize the data acquisition frequency to ensure that key mechanical behaviors are completely recorded. During the optimization process, it may be necessary to conduct multiple iterative simulations to gradually approach the optimal plan. The core of this step is to gradually improve the test plan through repeated adjustment and verification to ensure its scientificity and practicality. Finally, after multiple adjustments and optimizations, determine a scientific and reasonable rock dynamic test plan, which can accurately reflect the mechanical behavior of the target rock and meet the requirements of test accuracy and efficiency at the same time. This plan usually includes loading modes (such as uniaxial compression, triaxial compression, shear test, etc.), loading rates, and loading paths (such as step loading, cyclic loading, etc.), specimen size, and preparation requirements, etc. This plan will provide accurate guidance for subsequent actual loading tests, ensuring the reliability and engineering applicability of the test results. Through the above process, based on the adjustment analysis and optimization of the simulation test effect, a scientific and reasonable rock dynamic test plan can be formulated, laying a foundation for the accurate assessment of rock mechanical strength.

[0034] Use the intelligent loading unit to conduct a loading test on the rock specimen according to the rock dynamic test plan, and at the same time monitor the rock mechanical data stream and deformation data stream during the test process through the data acquisition unit.

[0035] In one embodiment, the intelligent loading unit applies a precisely controlled load to the rock specimen according to the loading mode (such as uniaxial compression, triaxial compression or shear test) and loading path (such as step loading, cyclic loading or dynamic impact loading) set in the rock dynamic test scheme. For example, in uniaxial compression testing, the loading unit gradually increases the axial pressure at the loading rate of the rock dynamic test scheme, while keeping the lateral direction free or applying a constant confining pressure to simulate the stress state in the real geological environment. During the loading process, the loading unit can adjust the loading rate and load magnitude in real time to ensure the high precision and stability of the test process. While conducting the loading test, the data acquisition unit monitors the mechanical response and deformation behavior of the rock specimen in real time through high-precision sensors, obtaining the rock mechanics data stream and deformation data stream. Among them, the mechanics data stream includes key parameters such as the stress, strain, load-displacement curve of the specimen; the deformation data stream records the local and overall deformation of the specimen through displacement sensors, strain gauges or optical measurement devices. For example, the displacement sensor can capture the axial and lateral deformations of the specimen during the loading process in real time, the strain gauge can measure the micro-strain distribution on the surface of the specimen, and the acoustic emission sensor can monitor the generation and propagation of internal cracks in the rock. Through the collaborative work of the intelligent loading unit and the data acquisition unit, the test process can comprehensively and accurately record the mechanical behavior and deformation characteristics of the rock specimen under dynamic loads. For example, in step loading testing, the data acquisition unit can capture the stress-strain response of the specimen under each level of load, as well as the non-linear deformation behavior of the specimen when approaching failure; in dynamic impact testing, the dynamic mechanical properties and failure modes of the specimen under instantaneous loads can be recorded. These data provide a rich information basis for subsequent rock mechanics strength analysis, ensuring a comprehensive evaluation of the rock mechanics properties.

[0036] Based on the above, the data processing unit calls the rock mechanics strength adaptive evaluation network.

[0037] In one embodiment, after receiving the real-time transmitted rock mechanics data stream and deformation data stream from the data acquisition unit, the data processing unit preprocesses these data, including denoising, normalization and format conversion, to ensure their quality and consistency. Subsequently, the data processing unit calls the pre-trained rock mechanics strength adaptive evaluation network, which is usually based on deep learning models (such as convolutional neural networks or recurrent neural networks), and can extract features from complex mechanics and deformation data and establish a non-linear mapping relationship between the input data and the rock mechanics strength. The advantage of this adaptive evaluation network is that it can dynamically adjust according to the changing test data, making the analysis of each test result more accurate, and can handle the complex performances of different rock samples in different environments, which makes the entire rock test process more intelligent and improves the efficiency and reliability of the evaluation.

[0038] Furthermore, the step of invoking the rock mechanics strength adaptive evaluation network based on the data processing unit includes:

[0039] Classify and label the rock mechanics strength index test database according to the mechanical strength test index set to obtain a mechanical strength index test data set; use a deep neural network to train the mechanical strength index test data set to obtain a set of mechanical strength index evaluation networks; fuse the set of mechanical strength index evaluation networks to generate a rock mechanics strength adaptive evaluation network, and store the rock mechanics strength adaptive evaluation network in the data processing unit.

[0040] Optionally, according to the mechanical strength test objectives (such as compressive strength, tensile strength, shear strength, etc.), classify the data in the rock mechanics strength index test database. For example, classify the data related to compressive strength (such as peak stress, elastic modulus, stress-strain curve) into one category, and the data related to tensile strength (such as fracture strength, tensile strain) into another category. Each category of data is labeled according to its corresponding mechanical index. For example, add the label "Compressive Strength" to the compressive strength data and the label "Tensile Strength" to the tensile strength data, thereby generating a structured mechanical strength index test data set, in which each category of data is clearly associated with its corresponding mechanical index. Subsequently, according to the classified and labeled data set, construct multiple deep neural network models, each model targeting a specific mechanical strength index. During the training process, divide the data set into a training set and a validation set, and optimize the network parameters through the backpropagation algorithm to enable the model to accurately predict the mechanical strength index. After training, perform cross-validation and performance evaluation on each model to ensure its prediction accuracy and generalization ability. Finally, obtain a set of mechanical strength index evaluation networks, each network dedicated to evaluating a specific mechanical strength index. After obtaining the set of mechanical strength index evaluation networks, assign weights to the outputs of each mechanical strength index evaluation network to determine the importance of each index in the comprehensive evaluation, and then use a weighted fusion method to integrate the outputs of each evaluation network to generate a comprehensive rock mechanics strength adaptive evaluation network. This network can simultaneously evaluate multiple mechanical strength indexes based on the input mechanical and deformation data and output a comprehensive mechanical strength analysis result. Finally, store the generated rock mechanics strength adaptive evaluation network in the data processing unit for subsequent test analysis and invocation. Through this process, a multi-dimensional and adaptive evaluation of the rock mechanics properties is achieved, significantly improving the efficiency and accuracy of the test analysis.

[0041] Furthermore, the step of obtaining the set of mechanical strength index evaluation networks includes:

[0042] The mechanical strength index test data set is trained using a deep neural network to obtain an initial index evaluation network set; the initial index evaluation network set is respectively subjected to cross-validation and iterative optimization to obtain the mechanical strength index evaluation network set.

[0043] Optionally, according to the classification identifier of the mechanical strength index test data set, multiple deep neural network models are constructed, each model corresponding to a mechanical strength index (such as compressive strength, tensile strength, shear strength, etc.). For example, for compressive strength data, a fully connected neural network (FCN) or a convolutional neural network (CNN) is constructed, and the input features include stress, strain, loading rate, etc., and the output is the predicted value of the compressive strength. During the training process, the data set is divided into a training set and a validation set, and the backpropagation algorithm is used to optimize the network parameters. Through multiple iterative trainings, the model can learn the non-linear mapping relationship of the mechanical strength index from the input data. After training, a set of initial index evaluation networks is obtained, and each network is dedicated to evaluating a specific mechanical strength index. Subsequently, the cross-validation method is used to evaluate the performance of each initial index evaluation network. For example, the data set is divided into K subsets, and K-1 subsets are used for training in turn, and the remaining 1 subset is used for validation, and this is repeated K times to ensure the generalization ability of the model. Through cross-validation, the prediction accuracy, stability, and overfitting situation of each network are evaluated. Then, according to the cross-validation results, the network is iteratively optimized. For example, if the network shows overfitting, overfitting can be reduced by increasing the regularization term (such as L2 regularization) or introducing a Dropout layer; if the prediction accuracy of the network is insufficient, the network structure can be adjusted (such as increasing the number of hidden layers or neurons) or the hyperparameters can be optimized (such as the learning rate, batch size). After multiple iterative optimizations, a set of high-performance mechanical strength index evaluation network sets is finally obtained, and each network can accurately and stably evaluate its corresponding mechanical strength index.

[0044] Furthermore, the generation of the rock mechanical strength adaptive evaluation network includes:

[0045] Weight distribution is performed on the mechanical strength index test data set to determine the mechanical index weight distribution factor; based on the mechanical index weight distribution factor, the mechanical strength index evaluation network set is weighted and fused to generate the rock mechanical strength adaptive evaluation network.

[0046] Optionally, according to engineering requirements or research objectives, clarify the importance of each mechanical strength index. For example, in the assessment of rock engineering stability, the compressive strength may be more critical than the tensile strength, so a higher weight is assigned to it. The weight assignment can be determined based on expert experience, historical data analysis, or quantitative methods such as the Analytic Hierarchy Process (AHP). For example, through the AHP, pairwise comparisons are made among various mechanical strength indexes (such as compressive strength, tensile strength, shear strength) to construct a judgment matrix, and the weight values of each index are calculated, thereby determining the weight distribution factors for each mechanical strength index. For example, the weight of compressive strength is 0.5, the weight of tensile strength is 0.3, and the weight of shear strength is 0.2. These weight factors reflect the relative importance of each index in the comprehensive evaluation. Subsequently, the output of each mechanical strength index evaluation network is multiplied by its corresponding weight factor to obtain the weighted evaluation result. For example, the output of the compressive strength evaluation network is multiplied by 0.5, the output of the tensile strength evaluation network is multiplied by 0.3, and the output of the shear strength evaluation network is multiplied by 0.2. Then, all the weighted evaluation results are summed to obtain the comprehensive rock mechanical strength evaluation value. Finally, the weighted fusion evaluation network is encapsulated into an overall rock mechanical strength adaptive evaluation network and stored in the data processing unit. This network can simultaneously evaluate multiple mechanical strength indexes based on the input mechanical and deformation data and output the comprehensive mechanical strength analysis result, providing a scientific basis for engineering applications.

[0047] Based on the rock mechanical strength adaptive evaluation network, perform strength evaluation on the rock mechanical data stream and deformation data stream to obtain the rock mechanical strength analysis result.

[0048] In one embodiment, first, the rock mechanical data stream (such as stress, strain, load-displacement curve) and the deformation data stream (such as displacement field distribution, fracture propagation pattern) are transmitted to the data processing unit in real time through the data acquisition unit. The data processing unit calls the pre-trained rock mechanical strength adaptive evaluation network to preprocess the input multi-source heterogeneous data and extract key features. For example, features such as peak stress and elastic modulus are extracted from the stress-strain curve, and local strain concentration regions or fracture propagation paths are extracted from the deformation data. Subsequently, the adaptive evaluation network respectively calls the internal mechanical strength index evaluation sub-networks (such as compressive strength evaluation network, tensile strength evaluation network, shear strength evaluation network) according to the extracted features to independently evaluate each mechanical strength index. The output result of each sub-network is multiplied by its corresponding weight factor to obtain the weighted evaluation value. Finally, the adaptive evaluation network synthesizes all the weighted evaluation values to generate the rock mechanical strength analysis result. These results provide a scientific basis for the assessment of rock engineering stability and design optimization, realizing the efficient and accurate evaluation of rock mechanical properties and significantly improving the intelligent and automated level of test analysis.

[0049] In summary, the embodiments of the present application at least have the following technical effects:

[0050] First, a rock test system is built. The rock test system includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit. Subsequently, according to the rock test standard, a rock specimen is prepared by the specimen preparation unit, and a test plan analysis is carried out on the rock specimen to obtain a rock dynamic test plan. Further, the intelligent loading unit is used to perform a loading test on the rock specimen according to the rock dynamic test plan, and at the same time, the rock mechanics data stream and deformation data stream during the test process are monitored through the data acquisition unit. After that, the rock mechanics strength adaptive evaluation network is called based on the data processing unit. Finally, based on the rock mechanics strength adaptive evaluation network, strength evaluation is carried out on the rock mechanics data stream and deformation data stream to obtain the rock mechanics strength analysis result. This solves the technical problem that the existing rock mechanics strength test method cannot evaluate the rock mechanics performance in real time and accurately due to low test accuracy and lagging data acquisition. By building an intelligent rock test system and combining it with the rock mechanics strength adaptive evaluation network, the technical effect of improving the accuracy and evaluation efficiency of the rock mechanics strength test is achieved.

[0051] Embodiment 2, based on the same inventive concept as the dynamic test analysis method of rock mechanics strength in the foregoing embodiment, as Figure 2 shown, the present application provides a dynamic test analysis system for rock mechanics strength. Among them, the system includes: a test system building component 11: building a rock test system, the rock test system including a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit; a test plan analysis component 12: preparing a rock specimen by the specimen preparation unit according to the rock test standard, and performing a test plan analysis on the rock specimen to obtain a rock dynamic test plan; a loading test component 13: using the intelligent loading unit to perform a loading test on the rock specimen according to the rock dynamic test plan, and at the same time, monitoring the rock mechanics data stream and deformation data stream during the test process through the data acquisition unit; an evaluation network calling component 14: calling the rock mechanics strength adaptive evaluation network based on the data processing unit; a strength evaluation component 15: performing strength evaluation on the rock mechanics data stream and deformation data stream based on the rock mechanics strength adaptive evaluation network to obtain the rock mechanics strength analysis result.

[0052] Furthermore, the test plan analysis component 12 is used to execute the following method:

[0053] Obtain the mechanical strength test objectives and rock geological conditions of the target rock; perform sample analysis on the mechanical strength test objectives according to the rock test standard to determine the sample preparation type and sample preparation specifications; perform sampling analysis on the rock geological conditions based on the rock test standard to determine the rock sampling location; call the rock sampling equipment through the sample preparation unit, and prepare samples of the target rock according to the sample preparation type, sample preparation specifications, and the rock sampling location to obtain the rock samples.

[0054] Further, the test plan analysis component 12 is used to execute the following method:

[0055] Obtain the mechanical strength test objectives of the rock samples, extract indicators from the mechanical strength test objectives to obtain a mechanical strength test index set; perform historical test data mining based on the mechanical strength test index set to obtain a rock mechanical strength index test database; perform correlation matching based on the attribute information of the target rock and the rock mechanical strength index test database to obtain a rock dynamic test plan.

[0056] Further, the test plan analysis component 12 is used to execute the following method:

[0057] Perform correlation matching based on the attribute information of the target rock and the rock mechanical strength index test database to determine a matching rock test plan; perform a mechanical strength simulation test on the target rock according to the matching rock test plan to obtain a mechanical strength simulation test effect; adjust and optimize the matching rock test plan based on the mechanical strength simulation test effect to obtain a rock dynamic test plan.

[0058] Further, the test plan analysis component 12 is used to execute the following method:

[0059] Perform adjustment analysis on the matching rock test plan based on the mechanical strength simulation test effect to determine the plan optimization direction; adjust and optimize the matching rock test plan according to the plan optimization direction to determine the rock dynamic test plan.

[0060] Further, the evaluation network calling component 14 is used to execute the following method:

[0061] Classify and label the rock mechanical strength index test database according to the mechanical strength test index set to obtain a mechanical strength index test data set; use a deep neural network to train the mechanical strength index test data set to obtain a mechanical strength index evaluation network set; fuse the mechanical strength index evaluation network set to generate a rock mechanical strength adaptive evaluation network, and store the rock mechanical strength adaptive evaluation network in the data processing unit.

[0062] Furthermore, the evaluation network calling component 14 is used to execute the following method:

[0063] Use a deep neural network to train the mechanical strength index test data set to obtain an initial index evaluation network set; perform cross-validation and iterative optimization on the initial index evaluation network set respectively to obtain the mechanical strength index evaluation network set.

[0064] Furthermore, the evaluation network calling component 14 is used to execute the following method:

[0065] Perform weight assignment on the mechanical strength index test data set to determine the mechanical index weight assignment factor; based on the mechanical index weight assignment factor, perform weighted fusion on the mechanical strength index evaluation network set to generate the rock mechanical strength adaptive evaluation network.

[0066] Embodiment 3: Based on the same inventive concept as the dynamic test analysis method for rock mechanical strength in the foregoing embodiments, the present application provides a medium in which a computer program is stored. When the processor executes the computer program, the following steps are implemented: Build a rock test system, which includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit; prepare a rock specimen through the specimen preparation unit according to the rock test standard, and perform test scheme analysis on the rock specimen to obtain a rock dynamic test scheme; use the intelligent loading unit to perform a loading test on the rock specimen according to the rock dynamic test scheme, and at the same time monitor the rock mechanical data stream and deformation data stream during the test process through the data acquisition unit; call the rock mechanical strength adaptive evaluation network based on the data processing unit; based on the rock mechanical strength adaptive evaluation network, perform strength evaluation on the rock mechanical data stream and deformation data stream to obtain the rock mechanical strength analysis result.

[0067] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0069] This specification and the drawings are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications therein.

Claims

1. A dynamic test and analysis method for rock mechanical strength, characterized in that, The method includes: Construct a rock testing system, which includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit; Prepare a rock specimen through the specimen preparation unit according to the rock testing standard, and analyze the test plan for the rock specimen to obtain a rock dynamic test plan; Use the intelligent loading unit to perform a loading test on the rock specimen according to the rock dynamic test plan, and simultaneously monitor the rock mechanics data stream and deformation data stream during the test process through the data acquisition unit; Based on the data processing unit, call the rock mechanics strength adaptive evaluation network; Based on the rock mechanics strength adaptive evaluation network, evaluate the strength of the rock mechanics data stream and deformation data stream to obtain the rock mechanics strength analysis result.

2. The dynamic test analysis method for rock mechanics strength according to claim 1, characterized in that, The step of preparing a rock specimen through the specimen preparation unit according to the rock testing standard includes: Obtain the mechanical strength test target and rock geological conditions of the target rock; Perform specimen analysis on the mechanical strength test target according to the rock testing standard to determine the specimen preparation type and specimen preparation specifications; Conduct sampling analysis on the rock geological conditions based on the rock testing standard to determine the rock sampling location; Call the rock sampling equipment through the specimen preparation unit, and prepare the target rock according to the specimen preparation type, specimen preparation specifications, and the rock sampling location to obtain the rock specimen.

3. The dynamic test analysis method for rock mechanical strength according to claim 2, characterized in that, The step of obtaining the rock dynamic test plan includes: Obtain the mechanical strength test target of the rock specimen, extract the indicators of the mechanical strength test target to obtain a mechanical strength test index set; Mine historical test data based on the mechanical strength test index set to obtain a rock mechanics strength index test database; Perform correlation matching based on the attribute information of the target rock and the rock mechanics strength index test database to obtain a rock dynamic test plan.

4. The dynamic test analysis method for rock mechanical strength according to claim 3, characterized in that The step of obtaining the rock dynamic test plan includes: Perform correlation matching based on the attribute information of the target rock and the rock mechanics strength index test database to determine a matching rock test plan; Perform a mechanical strength simulation test on the target rock according to the matching rock test plan to obtain the mechanical strength simulation test effect; Adjust and optimize the matching rock test plan based on the mechanical strength simulation test effect to obtain a rock dynamic test plan.

5. The dynamic test analysis method for rock mechanical strength according to claim 4, characterized in that The step of obtaining the rock dynamic test plan includes: Conduct adjustment analysis on the matching rock test plan based on the mechanical strength simulation test effect to determine the plan optimization direction; Adjust and optimize the matching rock test plan according to the plan optimization direction to determine the rock dynamic test plan.

6. The dynamic test analysis method for rock mechanical strength according to claim 3, characterized in that, The step of calling the rock mechanics strength adaptive evaluation network based on the data processing unit includes: Classify and label the rock mechanics strength index test database according to the mechanical strength test index set to obtain a mechanical strength index test data set; Use a deep neural network to train the mechanical strength index test data set to obtain a mechanical strength index evaluation network set; Fuse the mechanical strength index evaluation network set to generate an adaptive evaluation network for rock mechanical strength, and store the adaptive evaluation network for rock mechanical strength in the data processing unit.

7. The dynamic test analysis method for rock mechanical strength according to claim 6, characterized in that, The obtaining of the mechanical strength index evaluation network set includes: Use a deep neural network to train the mechanical strength index test data set to obtain an initial index evaluation network set; Perform cross-validation and iterative optimization on the initial index evaluation network set respectively to obtain the mechanical strength index evaluation network set.

8. The dynamic test analysis method for rock mechanical strength according to claim 6, characterized in that The generating of the adaptive evaluation network for rock mechanical strength includes: Perform weight assignment on the mechanical strength index test data set to determine the mechanical index weight assignment factor; Based on the mechanical index weight assignment factor, perform weighted fusion on the mechanical strength index evaluation network set to generate the adaptive evaluation network for rock mechanical strength.

9. The dynamic test and analysis system for rock mechanics strength is characterized in that, For implementing the dynamic test analysis method for rock mechanical strength according to any one of claims 1-8, the system includes: Test system building component: Build a rock test system, where the rock test system includes a specimen preparation unit, an intelligent loading unit, a data acquisition unit, and a data processing unit; Test plan analysis component: Prepare a rock specimen through the specimen preparation unit according to the rock test standard, and perform test plan analysis on the rock specimen to obtain a rock dynamic test plan; Loading test component: Use the intelligent loading unit to perform a loading test on the rock specimen according to the rock dynamic test plan, and simultaneously monitor the rock mechanical data stream and deformation data stream during the test process through the data acquisition unit; Evaluation network calling component: Call the adaptive evaluation network for rock mechanical strength based on the data processing unit; Strength evaluation component: Based on the adaptive evaluation network for rock mechanical strength, perform strength evaluation on the rock mechanical data stream and deformation data stream to obtain the analysis result of rock mechanical strength.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the dynamic test analysis method for rock mechanical strength according to any one of claims 1-8.

Images