Rock-soil mass parameter automatic correction method and system, electronic device and storage medium

Abstract

The application relates to the field of geotechnical engineering and automatic control technology, and discloses a rock-soil body parameter automatic correction method, a system, an electronic device and a storage medium.The method comprises the following steps: sensor network deployment and data acquisition; data preprocessing and abnormal value detection on the collected data; application of a mechanical behavior model and rock-soil body parameter correction; application of an optimization algorithm and optimization of key mechanical parameters; feedback calibration and correction parameter adjustment.The system comprises a sensor module, a data processing module, an optimization module and a calibration module.The electronic device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor.The application corrects key mechanical parameters by collecting stress and strain data of the rock-soil body in real time and combining the optimization algorithm, so that the rock-soil body parameters are kept highly consistent with actual working conditions through real-time monitoring and dynamic correction, and the correction accuracy and engineering safety are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of geotechnical engineering and automatic control technology, in particular to a geotechnical parameter automatic correction method and system, an electronic device and a storage medium. BACKGROUND

[0002] Geotechnical engineering plays a crucial role in modern construction, infrastructure development, and geological disaster prevention. In these projects, the accuracy of geotechnical parameters is fundamental to ensuring construction safety and structural stability. Geotechnical parameters such as elastic modulus, Poisson's ratio, and shear modulus not only describe the mechanical behavior of geotechnical bodies but also directly affect structural design, construction plan selection, and maintenance decisions.

[0003] Existing methods for obtaining and correcting geotechnical parameters mainly rely on two approaches: traditional laboratory tests, such as sampling, compression tests, and triaxial tests, to obtain mechanical parameters; and collecting stress, strain, displacement, and other data from field monitoring networks, which are then corrected using numerical models to help determine the actual bearing capacity and deformation characteristics of geotechnical bodies.

[0004] However, existing methods for correcting geotechnical parameters have low efficiency and limited accuracy due to manual data collection and analysis, and are susceptible to human factors. Most existing correction schemes are based on static preset models, but geotechnical bodies are influenced by multiple factors during actual construction, such as changes in groundwater levels and fluctuations in construction loads, resulting in correction results that cannot accurately reflect the true state of geotechnical bodies, affecting construction safety and progress. Moreover, there is a lack of real-time feedback mechanism, and the correction process cannot adjust geotechnical parameters based on real-time data, resulting in significant lag. Therefore, the present application provides a geotechnical parameter automatic correction method, system, electronic device, and storage medium to address the deficiencies in the prior art. SUMMARY

[0005] To address the deficiencies in the prior art, the present application provides a geotechnical parameter automatic correction method, system, electronic device, and storage medium, which solves the problem of low efficiency and limited accuracy of existing geotechnical parameter correction methods, which are susceptible to human factors and mostly based on static preset models. In actual construction, geotechnical bodies are influenced by multiple factors, resulting in correction results that cannot accurately reflect the true state of geotechnical bodies.

[0006] To achieve the above objectives, the present application is implemented through the following technical solutions: a geotechnical parameter automatic correction method, comprising the following steps:

[0007] The sensor installation position is determined by numerical simulation, the stress and strain parameters of the rock-soil body are collected in real time through the sensor network, and the collected data are transmitted to a data processing center;

[0008] The collected data are preprocessed, abnormal data are detected and removed using an abnormal value detection algorithm, and missing data are repaired using an interpolation method;

[0009] Based on the preprocessed data, a mechanical behavior model of the rock-soil body is applied to correct key mechanical parameters of the rock-soil body, including the elastic modulus and the Poisson's ratio;

[0010] An optimization algorithm is used to optimize the key mechanical parameters of the rock-soil body, a Lagrange multiplier method and a variation method are combined to minimize the correction error and satisfy the constraint condition, and the accuracy of the correction result is ensured;

[0011] According to the corrected key mechanical parameters of the rock-soil body, feedback calibration is performed, the error is calculated by comparing with subsequent real-time monitoring data, and the corrected key mechanical parameters are adjusted according to the feedback.

[0012] Preferably, the sensor installation position is determined by numerical simulation, and the numerical simulation step comprises: identifying a key area by analyzing the stress and strain distribution of the rock-soil body under different working conditions through numerical simulation;

[0013] The sensor layout is designed according to the simulation result to ensure monitoring of the key area;

[0014] The sensor installation position is optimized according to the characteristics of the rock-soil body, the deformation law and the construction conditions to ensure maximum data acquisition accuracy;

[0015] The layout density of the sensors is optimized to ensure comprehensive monitoring and improve data quality;

[0016] The simulation result is combined with the actual construction to adjust the sensor position and ensure accurate monitoring.

[0017] Preferably, the data preprocessing step comprises:

[0018] The original monitoring data transmitted by the sensors are obtained and preliminarily cleaned to remove noise and irrelevant data;

[0019] Standard deviation method and machine learning algorithm are used to identify and remove abnormal values, interpolation repair is performed on missing or abnormal data to ensure the integrity and accuracy of the data;

[0020] The data quality is evaluated to ensure that the preprocessed data meet the subsequent correction requirements.

[0021] Preferably, the step of reducing the dimensionality of the collected data comprises:

[0022] The collected high-dimensional data is converted into a tensor form, and a tensor decomposition technique is used to extract main features from the data;

[0023] The principal component analysis method is used to reduce the dimension of the data, and the component with the largest variance is retained, thereby reducing redundant information; and a feature selection method is used to further screen features most relevant to security threat analysis.

[0024] Preferably, the optimization algorithm comprises:

[0025] The Lagrange multiplier method and the variation method are used to optimize the key mechanical parameters of the rock-soil body, minimize the correction error, and satisfy the engineering constraint conditions;

[0026] The correction result is further optimized by polynomial regression and least squares method to ensure the accuracy of the corrected parameters and provide preliminary correction parameters for subsequent feedback calibration.

[0027] Preferably, the feedback calibration step comprises:

[0028] By comparing with subsequent real-time monitoring data, the correction error is calculated and the correction coefficient is adjusted, and the real-time monitoring data includes displacement data, environmental data, construction progress and load change;

[0029] The mean square error is used to evaluate the correction error, and the correction coefficient is dynamically adjusted through the adaptive feedback mechanism, and the formula is: ΔP adjusted = ΔP initial + γ × ΔP error ;

[0030] Wherein, ΔP adjusted is the adjusted rock-soil body parameter, ΔP initial is the preliminary correction value output by the optimization algorithm, γ is a dynamic abnormal constant ΔP error is the error between the actual measured value and the optimization result.

[0031] The correction parameter is updated according to the feedback result, and multiple iterations are performed to ensure the accuracy of the final correction result.

[0032] Preferably, the corrected key mechanical parameters are dynamically judged and adjusted by feedback gain and error threshold, and the formula is:

[0033] E adjusted = E new + K·(RMSE-threshold);

[0034] Wherein, E adjusted is the adjusted rock-soil body elastic modulus, E new is the newly corrected rock-soil body elastic modulus, K is the feedback gain, threshold is the preset error threshold, and RMSE is the root mean square error.

[0035] The application further provides a geotechnical parameter automatic correction electronic device system, comprising:

[0036] a sensor network for collecting stress and strain data of the geotechnical body in real time;

[0037] a data processing unit for pre-processing the collected data and correcting the mechanical parameters of the geotechnical body based on the pre-processed data; and an optimization module for executing an optimization algorithm to optimize the mechanical parameters of the geotechnical body and ensure the accuracy of the correction result.

[0038] a calibration module for adjusting the correction result according to real-time feedback to ensure the accuracy of the final correction parameters.

[0039] The application further provides a geotechnical parameter automatic correction electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor can implement the geotechnical parameter automatic correction method when executing the computer program.

[0040] The application further provides a geotechnical parameter automatic correction storage medium storing a computer program, wherein the computer program can implement the geotechnical parameter automatic correction method when executed by a processor.

[0041] The application provides a geotechnical parameter automatic correction method, system, electronic device and storage medium.

[0042] 1. The application combines the technical solutions of numerical simulation and sensor network, corrects key mechanical parameters by collecting stress and strain data of the geotechnical body in real time and combining an optimization algorithm, realizes real-time monitoring and dynamic correction to make the geotechnical parameters highly consistent with the actual working conditions, solves the problems of data deviation and correction lag caused by human factors, improves the correction accuracy and engineering safety compared with the manual collection and correction scheme in the prior art.

[0043] 2. The application combines multiple outlier detection algorithms with interpolation methods to ensure the accuracy and integrity of data in transmission and processing, effectively filters abnormal data and repairs missing data, ensures that subsequent model analysis is based on reliable data, solves the problem of missing or misjudged abnormal data in the data cleaning process compared with the single outlier processing method in the traditional technology, and improves the data quality and reliability of the analysis result.

[0044] 3、The present application combines the mechanical behavior model with the optimization algorithm, can dynamically adjust the key mechanical parameters of the rock-soil body based on the real-time monitoring data, achieves the effect that the corrected parameters are closer to the real working conditions through optimization and feedback calibration, compared with the fixed model and preset parameter mode in the prior art, the present application solves the problem that the model parameters cannot be corrected in time under complex working conditions, greatly improves the adaptability and precision.

[0045] 4、The present application adjusts the parameters after each feedback calibration through dynamic correction and multiple iteration optimization mechanism, achieves real-time optimization of the correction results, and can cope with the parameter changes under complex construction environment, compared with the static correction scheme in the prior art, solves the parameter correction lag problem caused by the asynchronous changes of the environment and construction progress, significantly improves the correction accuracy and reliability in the construction process. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 The method flowchart of the present application is shown in the figure;

[0047] Figure 2 The system architecture diagram of the present application is shown in the figure;

[0048] Figure 3 The computer device structure schematic diagram of the present application is shown in the figure.

[0049] Among them, 40, computer equipment;41, processor;42, memory;43, storage medium. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the specification of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0051] Please refer to the attached Figure 1 The rock-soil body parameter automatic correction method provided by the embodiments of the present application comprises the following steps:

[0052] S1, determine the sensor installation position by numerical simulation, collect the stress and strain parameters of the rock-soil body in real time through the sensor network, and transmit the collected data to the data processing center;

[0053] S2, pre-process the collected data, detect and remove abnormal data using an outlier detection algorithm, and repair missing data using an interpolation method;

[0054] S3, based on the pre-processed data, applying the mechanical behavior model of the rock-soil mass, correcting the key mechanical parameters of the rock-soil mass, the key mechanical parameters of the rock-soil mass including the elastic modulus and the Poisson's ratio;

[0055] S4, using an optimization algorithm to optimize the key mechanical parameters of the rock-soil mass, combining the Lagrange multiplier method and the variational method, minimizing the correction error and satisfying the constraint conditions, ensuring the accuracy of the correction results;

[0056] S5, according to the corrected key mechanical parameters of the rock-soil mass, feedback calibration is carried out, by comparing with the subsequent real-time monitoring data, calculating the error and adjusting the corrected key mechanical parameters according to the feedback.

[0057] For step S1, in this embodiment, the distribution characteristics of stress, strain and other properties of the rock-soil mass are analyzed by numerical simulation, combined with the physical properties of the target rock-soil mass, construction conditions and engineering requirements, the installation position of the sensor is selected. Numerical simulation can help identify possible risk areas and key areas in the rock-soil mass, so as to ensure that the sensor layout can cover all key parts. Through simulation calculation, the stress distribution, deformation trend and potential slip surface of the rock-soil mass under different working conditions can be obtained, which provides theoretical support for the best position of the sensor.

[0058] Specifically, the numerical simulation of the rock-soil mass is carried out by a mechanical model to comprehensively analyze the rock-soil mass. Numerical simulation techniques such as finite element method (FEM) or discrete element method (DEM) are used to simulate the mechanical behavior of the rock-soil mass under different loading conditions. By inputting the physical and mechanical parameters of the rock-soil mass (such as elastic modulus, Poisson's ratio, etc.) and boundary conditions, the stress and strain state of different regions can be calculated.

[0059] As an option, in the numerical simulation, the stress field of the rock-soil mass can be analyzed in detail by dividing it into different zones, combined with the mechanical parameters of different soil layers, to further optimize the layout of the sensors. In this layout strategy, the key areas (such as the perimeter of the foundation pit, the surrounding rock of the tunnel, the slope, etc. which may appear deformation) will be more densely laid out with sensors to ensure that the deformation of these areas can be more accurately monitored.

[0060] In one possible implementation, by considering different construction scenarios and natural disasters and other factors, combined with the specific needs of the project, the system automatically generates the optimal sensor layout scheme through the algorithm. This scheme not only considers the distribution of stress and strain, but also takes into account the communication distance between sensors, energy consumption, installation convenience and other practical factors.

[0061] In addition, during implementation, the sensor positions determined by numerical simulation will be actually applied to the construction site. Generally, the positions of the sensors will be dynamically adjusted according to the changes in the construction process, so as to timely respond to new monitoring requirements or abnormal situations. In the process of foundation pit construction, there may be stress concentration areas, at which time the system can re-distribute and encrypt the sensors through numerical simulation, to ensure accurate monitoring of these key areas.

[0062] Further, the sensor network also needs to have good real-time performance and efficient transmission capability when collecting data. Wireless ad hoc network technology is adopted, which can form stable communication links between sensor nodes without external network support. In some embodiments, low-power and high-reliability wireless communication protocols such as LoRa, ZigBee, etc. can be selected, which can ensure stable data transmission while reducing energy consumption.

[0063] Generally, the sensor network can transmit raw data to the data processing center with millisecond-level delay when collecting data in real time. The data collection process is not disturbed, so it can ensure real-time feedback of all key information and provide raw data support for subsequent preprocessing and correction.

[0064] Specifically, the sensor continuously monitors the stress and strain data of the rock-soil mass and sends the data to the data receiving center according to the set sampling frequency. In the receiving center, the data will be sorted and stored, and synchronized according to the time stamp of transmission. These data include but are not limited to stress, strain, displacement, temperature and other physical parameters of the rock-soil mass, and can provide support for subsequent correction calculations.

[0065] In some specific application scenarios in this embodiment, the installation of sensors is not limited to traditional soil, but also considers special areas such as rock-soil mass slopes, underground structures (such as tunnels, foundation pits, etc.). For these areas, the layout of the sensors will be more complex, and different depths and levels of monitoring requirements will be considered.

[0066] For step S2, in this embodiment, after data collection is completed, the raw data is first preliminarily cleaned to remove noise and irrelevant data, to ensure the accuracy of the data. The main goal of data cleaning is to remove outliers from the monitoring data to ensure that the subsequent processing process will not be disturbed. In order to achieve this goal, the present application adopts a variety of outlier detection methods to ensure that all types of abnormal data can be effectively identified and processed.

[0067] Generally, the data preprocessing step first uses the standard deviation method to detect outliers. Specifically, during monitoring, for each sensor collected parameter (such as stress, strain, displacement, etc.), according to statistical principles, if a data point is more than three times the standard deviation of the average value, the data point is considered an outlier. Through this method, those data points that deviate significantly from the normal range can be identified more quickly and effectively. The specific formula is as follows:

[0068] |x i -μ|>3σ;

[0069] where x i is the i-th data point, μ is the mean of the data, and σ is the standard deviation of the data. If the deviation of a data point exceeds three times the standard deviation, the point is marked as an outlier.

[0070] As an option, based on the standard deviation method, further outlier detection is performed in combination with the IsolationForest algorithm. The IsolationForest algorithm is a tree-based algorithm that judges the abnormality of data by constructing multiple decision trees. This method can more effectively identify outliers in high-dimensional data, especially for rare outliers in the data set. The algorithm judges the degree of abnormality by calculating the "isolation" degree of the sample, which is easier to distinguish outliers that differ greatly from other data points.

[0071] Specifically, when performing outlier detection, IsolationForest performs multiple random partitions on the data set and calculates the isolation degree of each data point. The isolation degree is used to determine whether it is an outlier. If a data point exhibits a high degree of isolation in most trees, it is considered an outlier. This method is particularly suitable for cases where there are multiple dimensions in the data and the distribution is complex.

[0072] In one possible implementation, for data points determined to be outliers, linear interpolation can be used for repair. Linear interpolation is a common data interpolation method that estimates and fills in missing or abnormal data based on the trend of adjacent data points. Specifically, if the data value of a sensor is determined to be abnormal, the data value of the adjacent time point of the sensor can be used to estimate the value of the abnormal data point through the interpolation formula:

[0073]

[0074] where x1, x2 are the known data points, y1, y2 are the known data points, x is the interpolation point, and y is the interpolation result. Through this method, the gap of abnormal data can be accurately filled, ensuring the continuity of the data.

[0075] In addition, for the detected outliers, it is also possible to choose to directly eliminate them. After eliminating the outliers, the system recalculates the mean and standard deviation of the remaining data to ensure the cleanliness and effectiveness of the data set. This approach is suitable for abnormal data that cannot be recovered by interpolation, avoiding the impact of false data on subsequent calculations and model correction.

[0076] In this embodiment, in order to further improve the data quality, a data quality evaluation and feedback mechanism is adopted. After completing the outlier cleaning, the system will evaluate the quality of the preprocessed data. The evaluation criteria mainly include the accuracy, completeness and consistency of the data. Specifically, the accuracy of the data refers to the degree of deviation between the data and the actual monitoring value; the completeness of the data refers to the degree of data loss or damage; the consistency of the data refers to the consistency between different sensor data. By establishing an evaluation index system, the system can generate a data quality report regularly and feedback to the monitoring personnel and data analysis team in a timely manner. If the evaluation result shows that the data quality is poor, the system will trace back to the data collection and transmission process to find and fix possible problems.

[0077] Specifically, in the data quality evaluation process, the system will evaluate the accuracy of the data according to the following formula:

[0078]

[0079] where Accuracy represents the average error between the predicted result and the actual value, is the predicted geotechnical parameter, y i is the actual measured geotechnical parameter, and n is the number of data points. Through this formula, the error between the preprocessed data and the actual monitoring data can be quantified, and the data quality can be further evaluated.

[0080] For step S3, in this embodiment, after data preprocessing and outlier detection, the mechanical behavior model of the geotechnical body is applied to correct the key mechanical parameters of the geotechnical body. Based on the cleaned and interpolated monitoring data, the mechanical behavior model is used to calculate the key mechanical parameters of the geotechnical body, including but not limited to the elastic modulus and Poisson's ratio. By correcting these mechanical parameters, the geotechnical body model can more accurately reflect the behavior of the geotechnical body under actual working conditions, thereby providing accurate input for subsequent optimization algorithms and feedback calibration.

[0081] Once the data is pre-processed, the cleaned data is used as input to a mechanical behavior model of the geotechnical body. The mechanical behavior model is used to describe the stress and strain response of the geotechnical body under external loads. In general, the behavior of the geotechnical body can be represented by classical constitutive models, such as elastic models, plastic models, and more complex nonlinear constitutive models.

[0082] In particular, the present application employs nonlinear constitutive models suitable for geotechnical bodies, such as the Modified Cam-Clay model or the Bouc-Wen model, to better simulate the deformation and rheological properties of the geotechnical body under different loads. These models connect the stress and strain relationship through mechanical equations, accurately describing the physical behavior of the geotechnical body under complex working conditions. The specific model can be represented as:

[0083] σ = f(ε, κ, p);

[0084] where σ is the stress of the geotechnical body, ε is the strain, κ is the plastic strain, p is the pore pressure, and the function f can represent different constitutive relationships. By adjusting these parameters, the changing behavior of the geotechnical body under different working conditions can be reflected. Especially when considering the complexity of the engineering environment, such as groundwater seepage, construction disturbance, etc., the accuracy of the mechanical model is crucial.

[0085] As an option, in some embodiments, the mechanical behavior model used can be further refined into a multi-level geological structure model to simulate the mechanical behavior of different soil layers. According to the different levels of the geotechnical body (such as sand, clay, rock, etc.), the selected constitutive model will be different. For clay layers, a model based on the Mohr-Coulomb criterion can be selected to describe its plastic behavior, while for sand layers, a more simplified elastic constitutive model can be used for description.

[0086] In general, during the correction process, an optimization algorithm is used to further ensure the accuracy and reasonableness of the correction results. The optimization algorithm can minimize the correction error and ensure that the corrected geotechnical body parameters meet various constraints of the project. In this embodiment, the optimization step in the correction process uses the Lagrange multiplier method and the variational method. Combined with these algorithms, the constraint conditions can be effectively handled, and the objective function can be optimized, so that the correction results not only conform to the physical law, but also meet the needs of engineering practice.

[0087] For example, when applying the Lagrange multiplier method, the optimization objective can be set to minimize the correction error, as follows:

[0088]

[0089] where to optimize the objective function, where E is the elastic modulus of the geotechnical body, v is the Poisson's ratio of the geotechnical body, σ measured is the measured stress value, and σ predicted is the stress value calculated based on the model, λ is the Lagrange multiplier, and constraint conditions represent physical limitations or engineering requirements in the optimization problem. The constraint conditions include the actual deformation capacity of the geotechnical body and the experimental test conditions.

[0090] As an option, in some embodiments, if the correction result of certain parameters exceeds the set range, the system will automatically adjust the correction algorithm and perform multiple iterations until the correction result meets the accuracy requirement. This iterative optimization process can effectively solve the problem of inaccurate parameters caused by external interference or changes in construction environment, ensuring the accuracy of the correction result of the geotechnical body parameters.

[0091] For step S4, in this embodiment, the accuracy and feasibility of the correction result are ensured by accurately adjusting the key parameters of the geotechnical body, such as the elastic modulus and Poisson's ratio. The optimization algorithm further improves the accuracy of the model through repeated adjustments during the correction process.

[0092] In this embodiment, the optimization algorithm mainly uses the combination of the Lagrange multiplier method and the variational method to optimize the key mechanical parameters of the geotechnical body. After the application of the mechanical behavior model of the geotechnical body, the parameter correction result may still have errors, so further correction is needed through the optimization algorithm. Specifically, the optimization algorithm will adjust according to the objective function to minimize the correction error and ensure that the correction result meets the engineering constraint conditions.

[0093] Generally, the Lagrange multiplier method is used to handle constrained optimization problems. The basic idea of the Lagrange multiplier method is to convert the constraint conditions into a part of the objective function, construct the Lagrange function, and solve the optimal solution by taking the derivative of the Lagrange function. For the optimization of geotechnical body parameters, the objective function can be represented as the sum of the squares of the correction errors, i.e., minimizing the correction error so that the corrected geotechnical body parameters are closer to the true values. The optimization objective function can be represented as:

[0094]

[0095] where, to optimize the objective function, where E is the elastic modulus of the geotechnical body, v is the Poisson's ratio of the geotechnical body, σ measured is the measured stress value, and σ predictedFor the stress value based on model calculation, λ is the Lagrange multiplier, constraint conditions represent physical limitations or engineering requirements in the optimization problem, and the constraint conditions include the actual deformation capacity of the rock-soil body and the experimental test conditions. By optimizing the Lagrange function, the optimal rock-soil body parameter correction value can be obtained, thereby ensuring the accuracy of the model.

[0096] Specifically, in the optimization process, the Lagrange multiplier method minimizes the correction error of the rock-soil body mechanical parameters, while considering the actual constraints in the working condition. In the correction process of the elastic modulus and Poisson's ratio of the rock-soil body, the optimization algorithm adjusts the values of these two parameters according to the stress and strain data in the actual working condition to meet the engineering design requirements and actual physical limitations.

[0097] As an option, to enhance the stability and accuracy of the optimization algorithm, the variational method can be combined for correction. The variational method is a mathematical method for solving optimization problems, which finds the optimal solution of the objective function by minimizing the variation. In the present application, the variational method is used to further optimize the correction error to ensure that the corrected rock-soil body parameters meet the actual requirements in engineering applications.

[0098] Specifically, the variational method optimizes the objective function through the variational principle, which can effectively handle optimization problems with multiple constraints. The goal of the optimization process is to minimize the correction error and meet a series of physical and engineering constraints. The application of the variational method enables the optimization process to more accurately reflect the actual state of the rock-soil body and provide real-time parameter correction in a constantly changing construction environment.

[0099] In one possible implementation, the iteration process of the optimization algorithm is adjusted by the following formula: E adjusted = E model + ΔE;

[0100] ν adjusted = v model + Δv;

[0101] where E adjusted is the adjusted rock-soil body elastic modulus, v adjusted is the adjusted Poisson's ratio, E model and v model represent the initial elastic modulus and Poisson's ratio based on the model, respectively, and ΔE and Δv are the correction amounts obtained by the optimization algorithm. The optimization algorithm repeatedly calculates and adjusts the correction amounts to minimize the prediction error, so that the corrected rock-soil body parameters are closer to the actual values.

[0102] In some embodiments, to further improve the efficiency of the optimization algorithm, heuristic algorithms such as genetic algorithms, simulated annealing algorithms, etc. can be used to assist the optimization process. These algorithms can quickly search for the global optimal solution, avoid falling into local optimal solution, and thus speed up the entire parameter optimization process. During construction, the continuous change of real-time data may require rapid adjustment of geotechnical parameters, so the use of heuristic optimization algorithms can significantly improve the response speed of the system.

[0103] For step S5, in this embodiment, the correction error is calculated by comparing the real-time monitoring data with the optimization results, and the correction parameters are dynamically adjusted according to the error feedback. The core goal of this step is to ensure that the corrected geotechnical parameters match the actual working conditions, thereby improving the accuracy of the correction results and ensuring that the geotechnical parameters are always highly consistent with the actual engineering requirements.

[0104] Generally, the calibration process is carried out as follows: first, the corrected geotechnical parameters are input into the real-time monitoring data, and the corresponding stress response is calculated according to the current monitoring data (such as strain, displacement, etc.). By comparing with the actual measured value, the error value is calculated. Specific error calculation can use common error evaluation indicators such as root mean square error RMSE or mean absolute error RMSE. Based on these error values, the system will adjust the correction parameters to reduce the difference between the model prediction value and the actual value.

[0105] Specifically, if there is a significant gap between the prediction results of the correction parameters and the subsequent real-time monitoring data, the system will adjust the correction parameters through a feedback mechanism. The formula of the feedback process can be expressed as:

[0106] E adjusted =E optimized +ΔE;

[0107] ν adjusted =ν optimized +Δν;

[0108] Where E adjusted is the adjusted geotechnical elastic modulus, v adjusted is the adjusted Poisson's ratio, E model and v model represent the initial elastic modulus and Poisson's ratio based on the model, respectively, ΔE is the correction amount of the elastic modulus, and Δv is the correction amount of the Poisson's ratio. By adjusting ΔE and Δv, the deviation between the predicted value and the actual value can be reduced, thereby continuously improving the accuracy of the geotechnical parameter correction.

[0109] As an alternative, an adaptive gain adjustment mechanism can also be incorporated during the feedback calibration process to further improve the calibration accuracy. Specifically, the adjustment amplitude of the feedback calibration is controlled by a gain coefficient, which can be dynamically adjusted to optimize the adjustment step size based on the error size of the real-time monitoring data. The implementation of this mechanism can use the following formula: AE = K RMSE;

[0110] Δv = K RMSE;

[0111] where AE is the correction amount of the elastic modulus, Δv is the correction amount of the Poisson's ratio, K is the feedback gain, RMSE is the root mean square error, and the difference between the correction result and the actual measurement value. According to the gain adjustment coefficient, the correction amount will be dynamically adjusted with the change of error, ensuring that each correction can effectively reduce the error range.

[0112] In one possible implementation, if the monitoring data shows that the error exceeds the set threshold (such as a certain maximum error limit), the system will automatically enter the calibration stage of multiple iterations, re-evaluate the corrected geotechnical parameters, and reduce the error to an acceptable range. This mechanism ensures that the correction process is always stable and effectively avoids the accumulation of errors.

[0113] In some embodiments, the calibration process is not limited to the correction of stress and strain parameters, but can also correct other parameters such as displacement and settlement according to the specific needs of the project. The calibration process is dynamic and can be adjusted in real time as the project progresses and the external environment changes, ensuring that the parameter correction is always highly consistent with the actual needs of the project.

[0114] Further, the feedback calibration mechanism of the present application is not only suitable for static correction tasks, but also can respond quickly when the state of the geotechnical mass changes during construction. In different construction stages, changes in geotechnical properties, construction loads, groundwater levels, and other factors may occur, so the system needs to adjust the correction strategy in real time based on new working condition data. This dynamic calibration process can ensure that the mechanical parameters of the geotechnical mass are accurately corrected in various complex environments.

[0115] The geotechnical parameter automatic correction system described below can be referred to in conjunction with the geotechnical parameter automatic correction method described above.

[0116] Please refer to the attached Figure 2 The present application also provides a geotechnical parameter automatic correction system, comprising:

[0117] A sensor network for real-time acquisition of stress and strain data of the geotechnical mass;

[0118] The data processing unit is configured to pre-process the collected data and correct the mechanical parameters of the rock-soil mass based on the pre-processed data; and the optimization module is configured to execute an optimization algorithm to optimize the mechanical parameters of the rock-soil mass and ensure the accuracy of the correction result.

[0119] The calibration module is configured to adjust the correction result according to real-time feedback and ensure the accuracy of the final correction parameter.

[0120] The system of the embodiment can be used to execute the method of the above embodiment, and has similar principles and technical effects, which will not be described here.

[0121] A computer device described below can be correspondingly referred to the rock-soil mass parameter automatic correction method described above.

[0122] Please refer to the accompanying drawings Figure 3 The present application also provides a computer device 40, comprising a processor 41 and a memory 42, the memory 42 stores a computer program executable by the processor, and the computer program is executed by the processor to perform the method as above.

[0123] The present application also provides a storage medium 43, which stores a computer program, and the computer program is executed by the processor 41 to perform the method as above.

[0124] The storage medium 43 can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0125] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for automatically correcting parameters of a geotechnical mass, characterized in that, The method comprises the following steps: Determine the sensor installation position by numerical simulation, collect the stress and strain parameters of the rock-soil mass in real time through the sensor network, and transmit the collected data to the data processing center; Preprocess the collected data through the data processing center, detect and remove abnormal data using an outlier detection algorithm, and repair missing data using an interpolation method; Based on the preprocessed data, correct the key mechanical parameters of the rock-soil mass, including the elastic modulus and Poisson's ratio, by applying a mechanical behavior model of the rock-soil mass; Optimize the key mechanical parameters of the rock-soil mass using an optimization algorithm, combine the Lagrange multiplier method and the variation method, minimize the correction error, and meet the constraint conditions; According to the corrected key mechanical parameters of the rock-soil mass, perform feedback calibration, compare with subsequent real-time monitoring data, calculate the error, and adjust the corrected key mechanical parameters according to the feedback; The step of numerical simulation comprises: Analyze the stress and strain distribution of the rock-soil mass under different working conditions through numerical simulation, and identify the key areas; Design the sensor layout according to the results of numerical simulation to ensure monitoring of the key areas; Optimize the sensor installation position based on the characteristics of the rock-soil mass, deformation law, and construction conditions to ensure maximum data collection accuracy; Optimize the layout density of the sensors to ensure comprehensive monitoring and improve data quality; Combine the simulation results with actual construction to adjust the sensor position to ensure accurate monitoring; The step of feedback calibration comprises: Compare with subsequent real-time monitoring data, including displacement data, environmental data, construction progress, and load changes, to calculate the correction error and adjust the correction coefficient; Use mean square error to evaluate the correction error and dynamically adjust the correction coefficient formula: ΔP adjusted = ΔP initial + γ x ΔP error ; Wherein, ΔP adjusted is the adjusted rock-soil parameter, ΔP initial is the preliminary correction value output by the optimization algorithm, γ is a dynamic abnormal constant, and ΔP error is the error between the actual measurement value and the optimization result. Update the correction parameters according to the feedback results and perform multiple iterations to ensure the accuracy of the final correction results; The corrected key mechanical parameters are dynamically adjusted by feedback gain and error threshold, and the formula is: E adjusted = E new + K · (RMSE-threshold); wherein E adjusted is the adjusted rock-soil elastic modulus, E new is the newly revised rock-soil elastic modulus, K is the feedback gain, threshold is the preset error threshold, and RMSE is the root mean square error.

2. The method of automatically revising geotechnical parameters according to claim 1, wherein, The step of preprocessing the collected data comprises: Obtain the original monitoring data transmitted by the sensors, perform preliminary cleaning, and remove noise and irrelevant data; Use standard deviation method and machine learning algorithm to identify and remove outliers, interpolate missing or abnormal data to ensure data integrity and accuracy; Evaluate data quality to ensure that the preprocessed data meet the subsequent correction requirements.

3. The method of claim 1, wherein The step of dimensionality reduction processing of the collected data comprises: Convert the collected high-dimensional data into tensor form, extract the main features of the data using tensor decomposition technology; Use principal component analysis method to reduce the dimensionality of the data, retain the components with the largest variance in the data, and thus reduce redundant information; Use feature selection method to further select features that are most relevant to security threat analysis.

4. The method for automatically correcting geotechnical parameters according to claim 1, wherein The optimization algorithm comprises: Use the Lagrange multiplier method and the variation method to optimize the key mechanical parameters of the rock-soil mass, minimize the correction error, and meet the engineering constraint conditions; Further optimize the correction results by polynomial regression and least squares method to ensure the accuracy of the corrected parameters and provide preliminary correction parameters for subsequent feedback calibration.

5. The system for automatically correcting geotechnical parameters, applied to the method for automatically correcting geotechnical parameters according to any one of claims 1 to 4, characterized in that, ​ A sensor module is configured to collect stress and strain data of the rock-soil mass in real time. A data processing module is configured to pre-process the collected data and correct the mechanical parameters of the rock-soil mass based on the pre-processed data. An optimization module is configured to optimize the mechanical parameters of the rock-soil mass by using an optimization algorithm to ensure the accuracy of the correction result. A calibration module is configured to adjust the correction result according to real-time feedback to ensure the accuracy of the final correction parameters.

6. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the rock-soil mass parameter automatic correction method according to any one of claims 1-4.

7. A storage medium for automatic correction of geotechnical parameters, characterized in that, The computer program is stored in the memory and is executed by the processor to implement the rock-soil mass parameter automatic correction method according to any one of claims 1-4.

Images