Intelligent prediction method and device for bearing capacity of pile foundation

Abstract

The invention provides an intelligent prediction method and device for the bearing capacity of a pile foundation, and the method comprises the steps: forming an in-situ test sample based on an engineering geology in-situ test; the optimal geological parameters of the karst geology are obtained through inversion of the proxy model; and geological parameters of the field test under multiple working conditions are obtained, and a pile foundation field test sample library is formed. Obtaining pile foundation bearing performance parameters of various karst geologies under a pile foundation reduced scale model experiment to form a pile foundation reduced scale model sample library; carrying out analogue simulation on the optimal geological parameters of each karst geology to form a pile foundation analogue simulation sample library; constructing a pile foundation bearing capacity training sample library by the three sample libraries; training the pile foundation bearing capacity prediction model; and geological parameters of a construction site are input into the pile foundation bearing capacity prediction model, and the pile foundation model of the actual construction site is optimized and adjusted based on the obtained geological parameters. According to the method, data of four research paradigms are fused, and a more comprehensive and accurate intelligent prediction method for the bearing capacity of the pile foundation is constructed.

Description

Technical Field

[0001] The present invention relates to the technical field of pile foundation bearing capacity monitoring, and in particular to a pile foundation bearing capacity intelligent prediction method and device. Background Art

[0002] In pile foundation tests in karst areas, scientific research usually adopts the following main paradigms: model test, simulation analysis, in-situ test, and data-driven.

[0003] Among them, the model test is to build a scaled-down karst model in a laboratory or a special test environment to simulate the actual karst geological conditions. By observing and measuring the loading, stress and deformation of the model, a preliminary understanding of the behavior of the pile foundation in the karst area can be obtained. This method can effectively reveal the response of the pile foundation under specific geological conditions, but its results need to be verified by actual conditions.

[0004] Simulation analysis is a virtual test of pile foundations in karst areas using computer modeling and numerical simulation technology. This method simulates the behavior of pile foundations under different loads and geological conditions by building complex geological and structural models. By adjusting the model parameters, the performance of pile foundations in various scenarios can be studied, providing an important reference for actual engineering design.

[0005] In-situ tests are direct tests conducted in actual karst areas, such as cone penetration tests (CPTs), in-situ shear tests, etc. These tests can provide real physical properties and mechanical parameters of soil and rock, thus helping to evaluate the performance of pile foundations under real conditions. In-situ tests are usually more realistic and accurate, but they are more costly and complex.

[0006] Data-driven is to predict and optimize the design and construction of pile foundations by analyzing a large amount of data collected on site, including geological survey data, pile foundation load test data, etc., combined with machine learning and data mining technology. This method can use historical data and real-time data for model training, thereby improving the accuracy of predicting pile foundation behavior in karst areas and the scientific nature of engineering decisions.

[0007] Although the three research paradigms of model testing, simulation analysis and in-situ testing generate a large amount of data, the research methods are relatively independent and the depth of integration is limited. Summary of the invention

[0008] The present invention provides a method and device for intelligent prediction of pile foundation bearing capacity, and constructs a more comprehensive and accurate method for intelligent prediction of pile foundation bearing capacity by integrating data from four research paradigms.

[0009] According to one aspect of the present invention, there is provided a method for intelligently predicting the bearing capacity of a pile foundation, comprising:

[0010] Based on the engineering in-situ test, a variety of geological parameters of karst geology are obtained, and one of the geological parameters of karst geology is used as a sample to form an in-situ test sample library;

[0011] Using the actual observation data of the karst geology, an inversion is performed based on the trained first pile foundation bearing capacity proxy model to obtain the optimal geological parameters of the karst geology;

[0012] Obtain geological parameters of field tests under multiple working conditions and form a sample library for pile foundation field tests;

[0013] Obtaining pile foundation bearing performance parameters of various karst geological conditions under pile foundation scale model experiments respectively, and forming a pile foundation scale model sample library;

[0014] Using the optimal geological parameters of the multiple karst geologies, respectively simulate the karst geology, calculate the pile foundation bearing performance parameters of the karst geology, and form a pile foundation simulation sample library;

[0015] The pile foundation field test sample library, the pile foundation scaled model sample library and the pile foundation simulation sample library are used together to construct a pile foundation bearing capacity training sample library;

[0016] The pile foundation bearing capacity training sample library is used to train the pile foundation bearing capacity prediction model;

[0017] Using actual construction site geological parameters as input into the trained pile foundation bearing capacity prediction model to obtain optimal geological parameters;

[0018] The pile foundation model of the actual construction site is optimized and adjusted based on the optimal geological parameters.

[0019] Optionally, the method further includes: comparing the geological parameters obtained based on the civil engineering in-situ test with the test results of the pile foundation scale model test; and adjusting the method of the pile foundation scale model test or adjusting the design of the pile foundation model according to the comparison result.

[0020] Optionally, it also includes: bringing the geological parameters of the various karst geologies at reduced sizes into the second pile foundation bearing capacity proxy model for inversion to obtain the optimal geological parameters of the various karst geologies at reduced sizes.

[0021] Optionally, before the geological parameters of the multiple karst geology under reduced size are brought into the second pile foundation bearing capacity proxy model for inversion to obtain the optimal geological parameters of the multiple karst geology under reduced size, the method further includes:

[0022] Selecting a training set, a test set and a validation set from the pile foundation scale model sample library;

[0023] Using the training set to train the second pile foundation bearing capacity proxy model;

[0024] optimizing the performance of the second pile foundation bearing capacity proxy model by adjusting hyperparameters, and evaluating the effect of the second pile foundation bearing capacity proxy model using the verification data;

[0025] The final performance of the second pile foundation bearing capacity proxy model is evaluated through the test set.

[0026] Optionally, the method further includes: simulating each of the karst geology according to the optimal geological parameters of the multiple karst geology under reduced size, calculating the pile foundation bearing capacity of each of the karst geology, obtaining a scaled simulation sample library, and supplementing the pile foundation scaled model sample library with the data of the scaled simulation sample library.

[0027] Optionally, it also includes: correcting the pile foundation simulation sample library obtained by simulation through the conversion relationship between the data of the pile foundation bearing field test of the various karst geology and the simulation data of each karst geology under the same working condition.

[0028] Optionally, before performing inversion based on the trained first pile foundation bearing capacity proxy model using the actual observed data of the karst geology to obtain the optimal geological parameters of the karst geology, the method further includes:

[0029] Selecting a training set, a test set and a validation set from the in situ test sample library;

[0030] Using the training set to train the first pile foundation bearing capacity proxy model;

[0031] Optimizing the performance of the first pile foundation bearing capacity proxy model by adjusting hyperparameters, and evaluating the effect of the first pile foundation bearing capacity proxy model using the verification data;

[0032] The final performance of the first pile foundation bearing capacity proxy model is evaluated through the test set.

[0033] Optionally, the optimal geological parameters of the multiple karst geologies are used to simulate each karst geology, and the pile foundation bearing capacity parameters of each karst geology are calculated to form a pile foundation simulation sample library, which also includes:

[0034] Using the pile foundation field test sample library, training the third pile foundation bearing capacity proxy model to adjust the parameters of the third pile foundation bearing capacity proxy model;

[0035] The optimal geological parameters are obtained by inverting the third pile foundation bearing capacity proxy model.

[0036] Optionally, before the training of the pile foundation bearing capacity prediction model using the training sample library, the method further includes:

[0037] The data in the training sample library are subjected to data preprocessing, noise reduction and feature extraction.

[0038] According to another aspect of the present invention, there is provided an intelligent prediction device for pile foundation bearing capacity, comprising:

[0039] A first sample acquisition unit is used to acquire geological parameters of various karst geologies based on an engineering in-situ test, and to form an in-situ test sample library by taking one of the geological parameters of the karst geology as a sample;

[0040] An inversion unit is used to perform inversion based on the trained first pile foundation bearing capacity proxy model using the actual observation data of the karst geology to obtain the optimal geological parameters of the karst geology;

[0041] The second sample acquisition unit is used to acquire geological parameters of field tests under multiple working conditions to form a pile foundation field test sample library;

[0042] The third sample acquisition unit is used to respectively acquire the pile foundation bearing performance parameters of the plurality of karst geology under the pile foundation scale model experiment to form a pile foundation scale model sample library;

[0043] A fourth sample acquisition unit is used to simulate each of the karst geology with the optimal geological parameters of the multiple karst geology, calculate the pile foundation bearing performance parameters of each karst geology, and form a pile foundation simulation sample library;

[0044] A fourth sample acquisition unit is used to construct a pile foundation bearing capacity training sample library by combining the pile foundation field test sample library, the pile foundation scaled model sample library and the pile foundation simulation sample library;

[0045] A training unit, used for training a pile foundation bearing capacity prediction model using the pile foundation bearing capacity training sample library;

[0046] A prediction unit, used to input the geological parameters of the pile foundation model at the actual construction site into the trained pile foundation bearing capacity prediction model to obtain the optimal geological parameters;

[0047] The model optimization unit is used to optimize and adjust the pile foundation model of the actual construction site based on the optimal geological parameters.

[0048] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0049] at least one processor; and

[0050] a memory communicatively connected to the at least one processor; wherein,

[0051] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent prediction method for pile foundation bearing capacity described in any embodiment of the present invention.

[0052] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the intelligent prediction method for pile foundation bearing capacity described in any embodiment of the present invention when executed.

[0053] The technical solution of the embodiment of the present invention forms a pile foundation field test sample library, a scaled model sample library obtained under the pile foundation scaled model experiment, and a simulation sample library obtained by the simulation experiment through the geological parameters of the field test under multiple working conditions, and together constructs a pile foundation bearing capacity training sample library, and trains the pile foundation bearing capacity prediction model, and then uses the geological parameters of the pile foundation model at the actual construction site to input into the trained pile foundation bearing capacity prediction model to obtain the optimal geological parameters; based on the optimal geological parameters, the pile foundation model at the actual construction site is optimized and adjusted. The present invention integrates the data of the four research paradigms to construct a more comprehensive and accurate intelligent prediction method for pile foundation bearing capacity.

[0054] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 A flowchart of a method for intelligently predicting pile foundation bearing capacity provided by an embodiment of the present invention;

[0057] Figure 2 A flowchart of another method for intelligently predicting pile foundation bearing capacity provided by an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of a model test device and rock layer distribution provided in one embodiment of the present invention;

[0059] Figure 4 A schematic diagram of the layout of the pile body optical fiber and strain gauge sensors provided in one embodiment of the present invention;

[0060] Figure 5 A schematic diagram of the layout of optical fibers on the top and sides of a cave provided in one embodiment of the present invention;

[0061] Figure 6 It is an overall schematic diagram of a test device in one embodiment of the present invention;

[0062] Figure 7 A schematic diagram of the structure of an intelligent prediction device for pile foundation bearing capacity provided by an embodiment of the present invention;

[0063] Figure 8 It is a structural schematic diagram of an electronic device for implementing an intelligent prediction method for pile foundation bearing capacity according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0065] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0066] Figure 1 The present invention provides a flowchart of a method for intelligently predicting the bearing capacity of a pile foundation. Figure 1 As shown, the method includes:

[0067] S101. Based on the engineering in-situ test, geological parameters of various karst geologies are obtained, and one of the geological parameters of the karst geology is used as a sample to form an in-situ test sample library.

[0068] The geological parameters of various karst geologies are collected through in-situ tests. The geological parameters include the physical properties of soil (such as density, water content, particle size distribution, etc.), mechanical properties (such as shear strength, compression modulus, etc.), structural characteristics of rocks, and environmental data (such as groundwater level, ground temperature, etc.). The geological parameters of a karst geology plus the geological type of the karst geology can be used as a data sample to form an in-situ test sample library that includes the characteristics of the geological parameters and the target output.

[0069] S102: performing inversion based on the trained first pile foundation bearing capacity proxy model using the actual observed data of the karst geology to obtain optimal geological parameters of the karst geology.

[0070] The first pile foundation bearing capacity proxy model is a prediction model constructed using a neural network model. The first pile foundation bearing capacity proxy model can be trained using data from an in-situ test sample library to construct a proxy model related to geological parameters. The purpose of the proxy model is to predict relevant geological parameters using input test data.

[0071] Inverse analysis refers to the reverse inference of geological parameters using the first pile foundation bearing capacity proxy model, that is, the actual geological parameters are reversed through the first pile foundation bearing capacity proxy model, which is used to adjust the parameters in the first pile foundation bearing capacity proxy model to match the actual observation data. Through inverse analysis, it is possible to identify which geological parameters best represent the characteristics of this type of karst geology.

[0072] The optimal geological parameters are usually those that can accurately describe the characteristics of this type of karst geology in the geological model and show the best performance in practical applications. Among them, the optimal parameters can minimize the error between the model's prediction results and the actual observation results. The optimal geological parameters can maintain the stability and reliability of the model under different conditions. And the optimal parameters should be able to truly reflect the actual characteristics and behaviors of the karst geological body.

[0073] S103. Obtain geological parameters of field tests under multiple working conditions to form a pile foundation field test sample library.

[0074] A typical geological length can be selected to carry out a field test of the pile foundation. In this way, the corresponding parameters under different working conditions, geological parameters, pile types and load requirements can be determined, including the characteristics of the karst environment, the design parameters of the pile foundation, and the type and size of the load. Based on the corresponding geological parameters, a representative test site can be selected to complete the field test under the geological parameters and working conditions. During the field experiment, the layout of the test piles, the load application method and the data collection method can also be adjusted, and then the field test is carried out according to the design plan. The field test can include static load tests or dynamic load tests. During the experiment, key data such as pile foundation settlement and applied load need to be recorded. In the data analysis stage, the test data needs to be analyzed in detail to evaluate the bearing capacity of the pile foundation under different working conditions and verify the pile foundation bearing capacity model. If problems are found during the experiment, the design or construction process can be adjusted to improve the applicability and reliability of the pile foundation. Finally, the data of the corresponding geological parameters under each working condition is formed as a sample to construct a sample library for pile foundation field tests.

[0075] S104, respectively obtaining pile foundation bearing performance parameters of the plurality of karst geological conditions under pile foundation scale model experiments to form a pile foundation scale model sample library.

[0076] The pile foundation scale model test is carried out to find out the bearing capacity of the pile foundation under different karst geological conditions. For example, the height and span of the caves in different karst geological conditions, the number of piles, the length of the piles, the pile diameter and other factors have a specific impact on the bearing capacity of the pile foundation. By setting different geological parameters, the bearing capacity of the pile foundation under different geological parameters can be obtained.

[0077] Physical scaled model tests can include analyzing the relationship between pile top load and rock destruction at the top of the cave, and the decrease in adhesion between the pile foundation and the rock stratum. Through physical scaled model tests, combined with numerical analysis technology, the changes in pile foundation bearing characteristics can be obtained. The pile foundation bearing characteristics include the attenuation relationship between pile top load and rock destruction at the top of the cave, and the adhesion between the pile foundation and the rock stratum, thereby forming a scaled model sample library. The data of pile foundation bearing capacity of a karst geology under a scaled model is used as a set of samples, and the sample data is converted to construct a model test pile foundation bearing capacity sample library.

[0078] S105, using the optimal geological parameters of the multiple karst geological conditions, respectively simulate the karst geological conditions, calculate the pile foundation bearing capacity parameters of the karst geological conditions, and form a pile foundation simulation sample library.

[0079] In view of the limitations of indoor model tests in terms of cycle and cost, it is impractical to carry out indoor model tests covering a variety of working conditions. Therefore, this embodiment adopts a simulation method, relying on finite element modeling technology to simulate geological parameters, environmental conditions, test conditions and other factors. By simulating a variety of geological parameters and karst conditions, the bearing capacity of karst pile foundations is calculated, thereby constructing a simulation sample library.

[0080] S106: Construct a pile foundation bearing capacity training sample library by combining the pile foundation field test sample library, the pile foundation scaled model sample library, and the pile foundation simulation sample library.

[0081] S107: using the pile foundation bearing capacity training sample library to train the pile foundation bearing capacity prediction model.

[0082] S108, using actual construction site geological parameters to input into the trained pile foundation bearing capacity prediction model to obtain optimal geological parameters.

[0083] In this embodiment, the pile foundation field test sample library, the pile foundation scale model sample library and the pile foundation simulation sample library are used to construct a training sample library, which is used to train the pile foundation bearing capacity prediction model. The pile foundation bearing capacity prediction model may include a BP neural network model, a Kriging model, a polynomial model, and the like.

[0084] In one embodiment, before training the pile foundation bearing capacity prediction model, the data in the training sample library can be preprocessed, denoised and feature extracted to ensure data consistency and accuracy, handle missing values ​​and outliers, and accurately capture the strain of the pile foundation. In addition, the data in the training sample library can be converted and proportionally adjusted to ensure that the pile foundation bearing capacity prediction model can accurately learn the complex relationship between various parameters. After the pile foundation bearing capacity prediction model is trained, the calculation formula of the pile foundation bearing capacity can be further optimized according to the optimal geological parameters output by it.

[0085] The output of the pile foundation bearing capacity prediction model is not only based on the comprehensiveness of the test and analysis data, but also takes into account the comprehensive influence of various geological parameters on the pile foundation behavior. The trained pile foundation bearing capacity prediction model can derive an accurate bearing capacity calculation formula suitable for pile foundations in karst areas, which can comprehensively consider the actual situation of field test data and the theoretical prediction of finite element analysis.

[0086] In the process of constructing the pile foundation bearing capacity prediction model, this embodiment adopts supervised learning or statistical analysis methods to correlate and analyze the collected strain data with historical and measured pile foundation bearing capacity data. The characteristics of the strain data may include the amplitude, frequency, rate of change, etc. of the strain signal. The effective selection of these features such as linear regression, decision tree, support vector machine (SVM) and neural network is used to train and construct the pile foundation bearing capacity prediction model to achieve accurate prediction of the pile foundation bearing capacity. In the training stage of constructing the pile foundation bearing capacity prediction model, cross-validation and parameter optimization techniques can also be used to improve the prediction accuracy and stability of the model.

[0087] In addition, the present embodiment can verify the pile foundation bearing capacity prediction model to evaluate its performance in predicting the pile foundation bearing capacity. The verification process can use techniques such as retention set evaluation and cross-validation to ensure that the model has good generalization ability and can effectively deal with unseen data. Once the pile foundation bearing capacity prediction model is verified, it can be applied to actual strain monitoring data to achieve real-time prediction and monitoring of pile foundation bearing capacity. The real-time collected strain data can be input into the trained pile foundation bearing capacity prediction model to evaluate the bearing capacity status of the pile foundation in real time.

[0088] S108. Optimizing and adjusting the pile foundation model of the actual construction site based on the optimal geological parameters.

[0089] When conducting on-site construction, first conduct a detailed geological survey to collect geological parameters and pile foundation bearing capacity data of the karst area; input the geological parameters into the pile foundation bearing capacity prediction model, and conduct a preliminary design of the pile foundation based on the prediction results of the pile foundation bearing capacity prediction model. The prediction result is the bearing capacity of a single pile foundation. During the preliminary design, it is necessary to design a pile group composed of multiple foundation piles based on the bearing capacity of a single pile foundation, and conduct a detailed analysis and optimize the design of the pile group; finally, apply the design scheme of the pile foundation model to on-site construction, and conduct real-time monitoring and feedback to continuously optimize the model and design scheme.

[0090] The technical solution of the embodiment of the present invention forms a pile foundation field test sample library, a scaled model sample library obtained under the pile foundation scaled model experiment, and a simulation sample library obtained by the simulation experiment through the geological parameters of the field test under multiple working conditions, and together constructs a pile foundation bearing capacity training sample library, and trains the pile foundation bearing capacity prediction model, and then uses the geological parameters of the pile foundation model at the actual construction site to input into the trained pile foundation bearing capacity prediction model to obtain the optimal geological parameters; based on the optimal geological parameters, the pile foundation model at the actual construction site is optimized and adjusted. The present invention integrates the data of the four research paradigms to construct a more comprehensive and accurate intelligent prediction method for pile foundation bearing capacity.

[0091] In one embodiment, the method further includes comparing the geological parameters obtained based on the civil engineering in-situ test with the test results of the pile foundation scale model test; and adjusting the method of the pile foundation scale model test or adjusting the design of the pile foundation model according to the comparison results.

[0092] Specifically, the scaled model experiment of pile foundation can use materials similar to those used in the civil engineering in-situ test. When selecting materials, it is necessary to consider their mechanical properties and other characteristics related to the research. In this embodiment, a group of model tests can be carried out based on the research on in-situ tests in karst areas, and the ratio of model tests to in-situ tests can be set to 1:30. In the model test, materials similar to those used in the civil engineering in-situ test can be selected. For example, a topless thickened tendon plastic water tank can be selected, and a stainless steel frame can be used to reinforce the outside. The burial depth of the cave is 50cm, and the location of the cave is 15cm 3 The cubic blocks are filled and it is considered that there is no filled cave. The pile foundation is selected as a three-pile cap pile foundation. The pile body is simulated by a plexiglass column with a diameter of 4 cm, and the pile body is embedded in the rock layer by 8 cm. The simulation of geological conditions is simplified, and different materials are used for casting at different depths. The proportion of similar materials is determined based on the test in the preliminary preparation stage. Among them, the medium-weathered marl is 47 cm, located in the lower layer of the model box, to simulate the bedrock and embedded rock mass of the prototype; the strongly weathered marl is 30 cm, simulating the overlying soil layer of the prototype. The rock layer depth and model schematic diagram are shown as follows Figure 3 As shown, Figure 3 (a) is a schematic diagram of the model test device of the present invention, Figure 3 (b) is a schematic diagram of rock layer distribution. The model materials selected for the test were determined based on the reference provided by the previous marl similar material test. River sand was used as aggregate, cement / gypsum was used as the main cementitious material, diatomaceous earth / red clay / marl powder was used as the regulating material, and the amount of mixing water was 1 / 7 of the mixing material. The density similarity ratio of the simulated material was 1.5, the internal friction angle similarity ratio was 1, and the strain similarity ratio was 1.

[0093] In the model test, sensors and instruments can be installed to measure the required physical quantities. In this case, fiber optic sensors and strain gauge sensors are arranged on the pile body, and fiber optic sensors are also arranged on the side and top plate of the cave. In order to obtain the strain data of the pile body, in addition to using traditional resistance strain gauges, fiber optic sensors are also arranged on the pile body. In order to avoid data loss due to deactivation of strain gauges during pouring and loading, strain gauges are symmetrically arranged at the same elevation to ensure data integrity. Details of the layout of pile body resistance strain gauges are as follows: Figure 4 As shown, Figure 4 (a) and (b) are schematic diagrams of the three-dimensional structure of the pile body. Figure 4(c) is a schematic diagram of the strain gauge sensor arranged on the pile body. Before the model was cast, the pile body strain sensor was laid out according to the test plan. Four layers were laid out within the thickness of the cave roof. The length of the optical fiber connecting the layers was 50 cm. The optical fiber on the side of the cave was fixed to a fiber net without strength according to the layout plan to facilitate laying and positioning during the model casting process. The optical fiber layout is as follows: Figure 5 As shown, Figure 5 (a)-(c) are schematic diagrams of the fiber optic layout on the top and side of the cave. In the model test, static strain collectors and AQ8603 fiber optic strain analyzers were used for data collection. After the model was cast, a certain humidity was maintained and the subsequent loading test was carried out after static curing for 21 days. During the model curing period, data was collected from the pile body strain sensor and the fiber optic sensors on the top and side of the cave every day to determine the survival status of the sensors. The model test loading system mainly consists of a reaction frame, a force transmission column, a hydraulic jack and a hydraulic pump; the measurement and reading system consists of a digital dial indicator and a load sensor with a display screen. The pile body was preloaded to ensure that the pile body and the jack fit tightly, and the initial loading data was collected and recorded. Gradual loading was carried out in the early stage, and graded loading was carried out in the later stage according to the actual test conditions and load-displacement curve. Data was collected during the load holding period until the model was destroyed. The integrity of the fiber optic monitoring range was ensured, and the required data was recorded and monitored in real time. These data will be used to analyze and compare the results of the model test with the results of the in-situ test. The results of the model test were analyzed and compared with the results of the in-situ test. The consistency and difference between the two are evaluated. Based on the comparison results, the model design or experimental method can be adjusted to improve the accuracy and reliability of the model.

[0094] The data of pile top displacement, strain and cave strain in the in-situ test and model test are collected and sorted again, and the data are processed using appropriate engineering or geological analysis tools, such as determining the load-displacement curve, stress-strain curve, etc. The test loading equipment should use hydraulic jacks, and the test loading and unloading methods should comply with the following regulations: 1. Loading should be carried out in stages, and equal loading should be adopted at each stage; the graded load should be 1 / 10 of the maximum loading value or the estimated ultimate bearing capacity, among which the first-stage loading amount can be twice the graded load; 2. Unloading should be carried out in stages, and the unloading amount of each stage should be twice the graded load during loading, and the unloading should be equal at each stage; 3. When loading and unloading, the load should be transferred evenly, continuously and without impact, and the change range of each level of load during the maintenance process should not exceed ±10% of the graded load. The test steps of the rapid maintenance load method are: 1. After each level of load is applied, it is maintained for 1 hour, and the pile top settlement is measured at 5 minutes, 15 minutes, and 30 minutes, and then measured every 15 minutes. 2. When the cumulative measurement time is 1 hour, if the pile top settlement increment in the last 15-minute time interval does not converge significantly compared with the pile top settlement increment in the adjacent 15-minute time interval, the load maintenance time should be extended until the settlement increment in the last 15 minutes is less than the settlement increment in the adjacent 15 minutes. 3. The conditions for terminating loading are as follows: (1) Under a certain load level, the settlement of the pile top is greater than 5 times the settlement under the previous load level, and the total settlement of the pile top exceeds 40 mm; (2) Under a certain load level, the settlement of the pile top is greater than 2 times the settlement under the previous load level, and has not reached the relative stability standard after 24 hours; (3) The maximum loading value required by the design has been reached and the settlement of the pile top has reached the relative stability standard; (4) When the engineering pile is used as an anchor pile, the pull-out amount of the anchor pile has reached the allowable value; (5) When the load-settlement curve is a slow-changing type, the pile top can be loaded to a total settlement of 60 mm to 80 mm; when the pile end resistance has not been fully exerted, the pile top can be loaded to a cumulative settlement of more than 80 mm. 4. When unloading, each load level is maintained for 15 minutes. After measuring the settlement of the pile top at the 5th and 15th minutes, the next load level can be unloaded. After unloading to zero, the residual settlement of the pile top should be measured and read for 1 hour, and the reading time should be 5 minutes, 15 minutes, and 30 minutes. When using the rapid method, all regions should summarize and accumulate experience, and can propose appropriate settlement relative stability control standards based on local conditions.The ultimate bearing capacity of pile foundation can be determined according to the load-displacement curve. When determining the vertical compressive bearing capacity of a single pile, the load-settlement (QS) curve and the settlement-logarithm of time (S-lgt) curve should be drawn. 1. Determine according to the characteristics of settlement change with load: for the steep drop QS curve, the load value corresponding to the starting point where the obvious steep drop occurs should be taken; 2. Determine according to the characteristics of settlement change with time: the load value of the previous level where the tail of the S-lgt curve shows an obvious downward bend should be taken; 3. For the slowly changing QS curve, it is advisable to take the load value corresponding to S equal to 40mm according to the total settlement of the pile top; for piles with D (D is the pile end diameter) greater than or equal to 800mm, the load value corresponding to S equal to 0.05D can be taken; when the pile length is greater than 40m, the elastic compression of the pile body should be considered. Evaluate the reliability and applicability of the experimental data, such as determining the strength, stiffness, plastic behavior and other parameters of the material. The specific device structure diagram of the model test is as follows. Figure 6 shown.

[0095] This embodiment also provides a flowchart of another method for intelligent prediction of pile foundation bearing capacity, such as Figure 2 As shown, Figure 2 The method also includes: bringing the geological parameters of the various karst geologies under reduced size into the second pile foundation bearing capacity proxy model for inversion to obtain the optimal geological parameters of the various karst geologies under reduced size.

[0096] The second pile foundation bearing capacity proxy model is a prediction model constructed using a neural network model. The second pile foundation bearing capacity proxy model can be trained using data from the scaled model sample library to construct a proxy model related to geological parameters. The purpose of the proxy model is to predict relevant geological parameters through input test data.

[0097] In one embodiment, the geological parameters of the multiple karst geology at the reduced size are brought into the second pile foundation bearing capacity proxy model for inversion to obtain the optimal geological parameters of the multiple karst geology at the reduced size, which also includes:

[0098] Selecting a training set, a test set and a validation set from the pile foundation scale model sample library;

[0099] Using the training set to train the second pile foundation bearing capacity proxy model;

[0100] optimizing the performance of the second pile foundation bearing capacity proxy model by adjusting hyperparameters, and evaluating the effect of the second pile foundation bearing capacity proxy model using the verification data;

[0101] The final performance of the second pile foundation bearing capacity proxy model is evaluated through the test set.

[0102] Specifically, data cleaning, standardization and feature selection can be performed on each sample in the data set of the scaled model sample library; training data, test data and verification data are selected from the scaled model sample library, and an appropriate neural network data model type is selected as the first pile foundation bearing capacity proxy model, and the model is trained using the training data. Subsequently, the model performance is optimized by adjusting the hyperparameters, and the model effect is evaluated using the verification data, and the parameters are further adjusted if necessary. Finally, the final performance of the model is evaluated on an independent test set.

[0103] Figure 2 The embodiment of the intelligent prediction method for pile foundation bearing capacity shown also includes: simulating each karst geology according to the optimal geological parameters of the multiple karst geologies under reduced size, calculating the pile foundation bearing capacity of each karst geology, obtaining a scaled simulation sample library, and supplementing the pile foundation scaled model sample library with the data of the scaled simulation sample library.

[0104] For the optimal geological parameters of various karst geological conditions under reduced sizes, simulation can be performed to calculate the bearing capacity of pile foundations, and a scaled simulation sample library can be obtained to supplement the scaled model sample library.

[0105] Figure 2 In the embodiment of the intelligent prediction method for pile foundation bearing capacity shown in the figure, the optimal geological parameters of the karst geology are obtained by inversion based on the trained first pile foundation bearing capacity proxy model with the actual observation data of the karst geology, which also includes:

[0106] Selecting a training set, a test set and a validation set from the in situ test sample library;

[0107] Using the training set to train the first pile foundation bearing capacity proxy model;

[0108] Optimizing the performance of the first pile foundation bearing capacity proxy model by adjusting hyperparameters, and evaluating the effect of the first pile foundation bearing capacity proxy model using the verification data;

[0109] The final performance of the first pile foundation bearing capacity proxy model is evaluated through the test set.

[0110] Specifically, data cleaning, standardization and feature selection can be performed on each sample in the data set of the in-situ test sample library; training data, test data and verification data are selected from the in-situ test sample library, and an appropriate neural network data model type is selected as the first pile foundation bearing capacity proxy model, and the model is trained using the training data. Subsequently, the model performance is optimized by adjusting the hyperparameters, and the model effect is evaluated using the verification data, and the parameters are further adjusted if necessary. Finally, the final performance of the model is evaluated on an independent test set.

[0111] Figure 2 In the embodiment of the intelligent prediction method for pile foundation bearing capacity shown in the figure, the optimal geological parameters of the multiple karst geologies are used to simulate each karst geology, and the pile foundation bearing capacity parameters of each karst geology are calculated to form a pile foundation simulation sample library, which also includes:

[0112] Using the pile foundation field test sample library, training the third pile foundation bearing capacity proxy model to adjust the parameters of the third pile foundation bearing capacity proxy model;

[0113] The optimal geological parameters are obtained by inverting the third pile foundation bearing capacity proxy model.

[0114] This embodiment obtains some accurate actual geological parameters through full-scale on-site construction, which are used to adjust the parameters of the third pile foundation bearing capacity proxy model so that its output matches the actual test data as much as possible, involving optimization algorithms and data fitting and other technologies. In this way, the optimal geological parameters under different working conditions can be obtained, and simulation can be performed based on the optimal geological parameters under different working conditions, so that the boundary conditions, cave size and location of the finite element simulation are more accurate, ensuring that the performance of the proxy model obtained by inversion under different working conditions is consistent with the actual test data.

[0115] The embodiment of the present invention combines experimental data, numerical simulation and machine learning methods, takes the data of in-situ test, model test and finite element simulation, including stress, strain, load, characteristic points of settlement curve and curve shape parameters, as input data, and divides them to obtain training set and test set in the data set, takes the parameters as input sample library, trains the neural network, and finds the optimal parameter group. The algorithm has adaptive ability, can adjust the model parameters according to different karst geological conditions, and improves the prediction accuracy and applicability. Combined with a large amount of geological data and real-time monitoring data, the machine learning algorithm is used to analyze and predict the impact of stratum changes on pile foundation stability. Through machine learning technology, the reliability and prediction accuracy of pile foundation construction in karst geological environment are improved. Reduce the additional costs and delays caused by geological risks, and optimize engineering management and resource utilization. Provide an intelligent decision support system to help engineering teams make timely and accurate decisions in complex geological environments.

[0116] Figure 7 This is a schematic diagram of the structure of a pile foundation bearing capacity intelligent prediction device provided in the third embodiment of the present invention. Figure 7 As shown, the device comprises:

[0117] The first sample acquisition unit 701 is used to acquire geological parameters of various karst geologies based on engineering in-situ tests, and to form an in-situ test sample library by taking one of the geological parameters of the karst geology as a sample;

[0118] An inversion unit 702 is used to perform inversion based on the trained first pile foundation bearing capacity proxy model using the actual observation data of the karst geology to obtain the optimal geological parameters of the karst geology;

[0119] The second sample acquisition unit 703 is used to acquire geological parameters of field tests under multiple working conditions to form a pile foundation field test sample library;

[0120] The third sample acquisition unit 704 is used to respectively acquire pile foundation bearing performance parameters of various karst geological conditions under pile foundation scale model experiments to form a pile foundation scale model sample library;

[0121] The fourth sample acquisition unit 705 is used to simulate each of the karst geology with the optimal geological parameters of the multiple karst geology, calculate the pile foundation bearing performance parameters of each karst geology, and form a pile foundation simulation sample library;

[0122] A fourth sample acquisition unit 706 is used to construct a pile foundation bearing capacity training sample library by combining the pile foundation field test sample library, the pile foundation scaled model sample library and the pile foundation simulation sample library;

[0123] A training unit 707, used to train a pile foundation bearing capacity prediction model using the pile foundation bearing capacity training sample library;

[0124] The prediction unit 708 is used to input the geological parameters of the pile foundation model at the actual construction site into the trained pile foundation bearing capacity prediction model to obtain the optimal geological parameters;

[0125] The model optimization unit 709 is used to optimize and adjust the pile foundation model of the actual construction site based on the optimal geological parameters.

[0126] The intelligent prediction device for pile foundation bearing capacity provided in the embodiment of the present invention can execute the intelligent prediction device for pile foundation bearing capacity provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0127] Figure 8A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0128] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0129] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0130] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for intelligent prediction of pile foundation bearing capacity.

[0131] In some embodiments, a pile foundation bearing capacity intelligent prediction method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the pile foundation bearing capacity intelligent prediction method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform a pile foundation bearing capacity intelligent prediction method in any other appropriate manner (for example, by means of firmware).

[0132] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0134] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0136] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0137] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0138] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0139] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligent prediction of pile foundation bearing capacity, characterized in that: include: Based on the engineering in-situ test, a variety of geological parameters of karst geology are obtained, and one of the geological parameters of karst geology is used as a sample to form an in-situ test sample library; Using the actual observation data of the karst geology, an inversion is performed based on the trained first pile foundation bearing capacity proxy model to obtain the optimal geological parameters of the karst geology; Obtain geological parameters of field tests under multiple working conditions and form a sample library for pile foundation field tests; Obtaining pile foundation bearing performance parameters of various karst geological conditions under pile foundation scale model experiments respectively, and forming a pile foundation scale model sample library; Using the optimal geological parameters of the multiple karst geologies, respectively simulate the karst geology, calculate the pile foundation bearing performance parameters of the karst geology, and form a pile foundation simulation sample library; The pile foundation field test sample library, the pile foundation scaled model sample library and the pile foundation simulation sample library are used together to construct a pile foundation bearing capacity training sample library; The pile foundation bearing capacity training sample library is used to train the pile foundation bearing capacity prediction model; Using actual construction site geological parameters as input into the trained pile foundation bearing capacity prediction model to obtain optimal geological parameters; The pile foundation model of the actual construction site is optimized and adjusted based on the optimal geological parameters.

2. The intelligent prediction method for pile foundation bearing capacity according to claim 1 is characterized in that: Also includes: Comparing the geological parameters obtained based on the civil engineering in-situ test with the test results of the pile foundation scale model test; The method of the pile foundation scale model experiment is adjusted or the design of the pile foundation model is adjusted according to the comparison result.

3. The intelligent prediction method for pile foundation bearing capacity according to claim 1, characterized in that: Also includes: The geological parameters of the various karst geologies under reduced size are brought into the second pile foundation bearing capacity proxy model for inversion to obtain the optimal geological parameters of the various karst geologies under reduced size.

4. The intelligent prediction method for pile foundation bearing capacity according to claim 3 is characterized in that: The method of bringing the geological parameters of the various karst geologies under reduced size into the second pile foundation bearing capacity proxy model for inversion to obtain the optimal geological parameters of the various karst geologies under reduced size also includes: Selecting a training set, a test set and a validation set from the pile foundation scale model sample library; Using the training set to train the second pile foundation bearing capacity proxy model; Optimizing the performance of the second pile foundation bearing capacity proxy model by adjusting hyperparameters, and evaluating the effect of the second pile foundation bearing capacity proxy model using the verification data; The final performance of the second pile foundation bearing capacity proxy model is evaluated through the test set.

5. The intelligent prediction method for pile foundation bearing capacity according to claim 3 is characterized in that: Also includes: The optimal geological parameters of the various karst geological conditions under reduced size are used to simulate the karst geological conditions respectively, and the pile foundation bearing capacity of each karst geological condition is calculated to obtain a scaled simulation sample library, and the data of the scaled simulation sample library are used to supplement the pile foundation scaled model sample library.

6. The intelligent prediction method for pile foundation bearing capacity according to claim 1, characterized in that: Also includes: The pile foundation simulation sample library obtained by simulation is corrected through the conversion relationship between the data of the pile foundation bearing field test of various karst geology and the simulation data of each karst geology under the same working condition.

7. The intelligent prediction method for pile foundation bearing capacity according to claim 1, characterized in that: The method further includes: performing inversion based on the trained first pile foundation bearing capacity proxy model using the actual observed data of the karst geology to obtain the optimal geological parameters of the karst geology; Selecting a training set, a test set and a validation set from the in situ test sample library; Using the training set to train the first pile foundation bearing capacity proxy model; Optimizing the performance of the first pile foundation bearing capacity proxy model by adjusting hyperparameters, and evaluating the effect of the first pile foundation bearing capacity proxy model using the verification data; The final performance of the first pile foundation bearing capacity proxy model is evaluated through the test set.

8. The intelligent prediction method for pile foundation bearing capacity according to claim 1, characterized in that: The optimal geological parameters of the multiple karst geological conditions are used to simulate the karst geological conditions respectively, and the pile foundation bearing capacity parameters of the karst geological conditions are calculated to form a pile foundation simulation sample library, which also includes: Using the pile foundation field test sample library, training the third pile foundation bearing capacity proxy model to adjust the parameters of the third pile foundation bearing capacity proxy model; The optimal geological parameters are obtained by inverting the third pile foundation bearing capacity proxy model.

9. The intelligent prediction method for pile foundation bearing capacity according to claim 1, characterized in that: Before the training of the pile foundation bearing capacity prediction model using the training sample library, the method further includes: The data in the training sample library are subjected to data preprocessing, noise reduction and feature extraction.

10. An intelligent prediction device for pile foundation bearing capacity, characterized in that: include: A first sample acquisition unit is used to acquire geological parameters of various karst geologies based on an engineering in-situ test, and to form an in-situ test sample library by taking one of the geological parameters of the karst geology as a sample; An inversion unit is used to perform inversion based on the trained first pile foundation bearing capacity proxy model using the actual observation data of the karst geology to obtain the optimal geological parameters of the karst geology; The second sample acquisition unit is used to acquire geological parameters of field tests under multiple working conditions to form a pile foundation field test sample library; The third sample acquisition unit is used to respectively acquire the pile foundation bearing performance parameters of the plurality of karst geology under the pile foundation scale model experiment to form a pile foundation scale model sample library; A fourth sample acquisition unit is used to simulate each of the karst geology with the optimal geological parameters of the multiple karst geology, calculate the pile foundation bearing performance parameters of each karst geology, and form a pile foundation simulation sample library; A fourth sample acquisition unit is used to construct a pile foundation bearing capacity training sample library by combining the pile foundation field test sample library, the pile foundation scaled model sample library and the pile foundation simulation sample library; A training unit, used for training a pile foundation bearing capacity prediction model using the pile foundation bearing capacity training sample library; A prediction unit, used to input the geological parameters of the pile foundation model at the actual construction site into the trained pile foundation bearing capacity prediction model to obtain the optimal geological parameters; The model optimization unit is used to optimize and adjust the pile foundation model of the actual construction site based on the optimal geological parameters.

Images