A method and system for automatic optimization of pile position in thick soft soil

Abstract

The present invention discloses a method and system for automatic optimization of pile positions suitable for thick soft soil. The method comprises: obtaining the pile foundation design drawing data of the target project and determining the initial design scheme of the pile position; evaluating the adaptability of the initial design scheme according to the geological parameters of the construction location, and if the adaptability is less than the threshold, optimizing based on the genetic algorithm to generate an optimization scheme; constructing the pile foundation according to the optimization scheme, and monitoring the stress changes on the pile foundation surface in real time, predicting the future stress changes and evaluating the uniformity of stress distribution; and finally determining the pile foundation design and implementation plan according to the evaluation results. The method improves the adaptability and safety of pile foundation design and construction.

Description

Technical Field

[0001] The invention relates to the technical field of pile foundation construction, and in particular to a method and system for automatically optimizing pile positions suitable for thick soft soil. Background Art

[0002] In order to ensure the long-term stability of the target project in soft soil areas, pile foundation has become one of the commonly used foundation treatment methods. Pile foundation transfers the load of the building to the deeper soil or rock layer, thereby effectively improving the bearing capacity of the foundation and reducing settlement.

[0003] Traditional design methods often fail to fully consider the interaction between pile foundation and geological structure, resulting in the pile foundation settlement risk and bearing capacity failing to achieve the expected results. Therefore, how to optimize the pile position design, reduce the pile foundation settlement risk, and improve the pile foundation bearing capacity based on geological parameters has become an urgent problem to be solved in the current construction engineering field.

[0004] The application of intelligent optimization technologies such as genetic algorithms and convolutional neural networks has gradually entered the field of pile foundation design. Automatically adjusting the pile position design scheme through intelligent optimization algorithms can better adapt to complex geological conditions and improve the rationality and reliability of the design scheme. In addition, through real-time monitoring of stress sensors and stress change prediction models based on long short-term memory networks (LSTM), the long-term stability of pile foundations can be effectively evaluated, providing a decision-making basis for subsequent pile foundation design and construction plans.

[0005] However, the existing pile foundation design methods and systems still have some shortcomings, such as the lack of automatic optimization mechanism for complex geological conditions, the difficulty in achieving effective connection between the various links in the design and construction process, and the limited accuracy of real-time monitoring and prediction of pile foundation stress distribution. Therefore, an automatic pile position adjustment method and system suitable for deep soft soil is proposed to solve the above problems and improve the scientificity and engineering effect of pile foundation design and construction, which has important practical significance. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes a method and system for automatically optimizing pile positions in thick soft soil.

[0007] A first aspect of the present invention provides a method for automatically optimizing pile positions in thick soft soil, comprising:

[0008] Obtaining pile foundation design drawing data of the target project, and determining an initial design scheme for pile positions of the target project according to the design drawing data;

[0009] Acquire geological parameters of the target engineering construction location, and perform adaptability evaluation on the initial design scheme of the pile position according to the geological parameters to obtain adaptability evaluation results;

[0010] If the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on a genetic algorithm to obtain an optimized pile position design scheme;

[0011] Perform pile foundation construction according to the pile position design optimization plan, monitor the pile foundation surface stress change data in real time, predict the stress change in a future preset time period according to the pile foundation surface stress change data, and obtain the stress change prediction result;

[0012] Evaluate the uniformity of the stress distribution on the pile foundation surface at each time point in a future preset time period according to the stress change prediction result, and obtain an evaluation result of the uniformity of the stress distribution on the pile foundation surface;

[0013] The pile foundation design and construction plan are determined based on the pile foundation surface stress distribution uniformity assessment results.

[0014] In this solution, the pile foundation design drawing data of the target project is obtained, and the initial design scheme of the pile position of the target project is determined according to the design drawing data, specifically:

[0015] Acquire the pile foundation design drawing data of the target project, convert the pile foundation design drawing data into an electronic image, and obtain an electronic design drawing;

[0016] Obtaining a legend of the pile foundation design drawing, marking the legend with corresponding component names, and obtaining a name-marked legend;

[0017] A pile foundation recognition model is constructed based on a convolutional neural network, an input layer, a convolutional layer, an activation function, a pooling layer, a fully connected layer, and an output layer of the pile foundation recognition model are set, and a name annotation legend is imported into the pile foundation recognition model for model training;

[0018] The electronic design drawing is imported into the trained pile foundation recognition model to perform pile foundation recognition, and an initial design scheme of pile positions of the target project is determined according to the recognition result. The initial design scheme of pile positions includes the number of pile foundations, pile foundation diameter and length, and pile foundation position.

[0019] In this solution, the geological parameters of the target engineering construction location are obtained, and the adaptability of the initial design scheme of the pile position is evaluated according to the geological parameters to obtain the adaptability evaluation results, which are specifically:

[0020] Obtaining geological parameters of the target engineering construction location, including soil type, distribution, thickness, density, porosity, and water content of each soil layer;

[0021] Constructing a three-dimensional model of the geological structure of the target engineering construction location according to the geological parameters, and constructing a three-dimensional model of the pile foundation according to the initial design plan of the pile position;

[0022] According to the pile position initial design scheme, the pile foundation three-dimensional model is simulated and constructed in the geological structure three-dimensional model to obtain a simulated three-dimensional model;

[0023] Obtaining the relationship data of the impact of compression on the soft soil geological parameters of each soil layer, adjusting the geological parameters of the target engineering construction location after simulation and construction according to the relationship data of the impact of the change, and obtaining the geological update parameters;

[0024] Based on the finite element analysis method, the soil layer in the simulated three-dimensional model is divided into N finite element grids according to the preset size, and the geological update parameters are mapped to each finite element grid;

[0025] Obtaining pile foundation surface roughness data, calculating and determining the load capacity data of each finite element grid for the pile foundation according to the geological update parameters and the pile foundation surface roughness data, and constructing a pile foundation settlement simulation model according to the load capacity data of each finite element grid for the pile foundation;

[0026] Constructing a settlement numerical simulation model based on the bearing capacity data of the pile foundation of each finite element grid, obtaining the bearing capacity data of the soil layer at the construction location of the target project for the target project and the minimum bearing capacity data of the soil layer required for constructing the target project;

[0027] Calculating the required bearing capacity of the pile foundation for the target project based on the bearing capacity data of the soil layer for the target project and the minimum bearing capacity data of the soil layer required for constructing the target project;

[0028] Calculating the minimum bearing capacity of each pile foundation in the target project according to the required bearing capacity of the pile foundation for the target project, applying the minimum bearing capacity of each pile foundation to each pile foundation in the target project according to the pile foundation settlement simulation model, evaluating the settlement risk of each pile foundation, and obtaining settlement risk data;

[0029] The adaptability of the initial design scheme of the pile position in the soil layer of the construction location of the target project is evaluated based on the settlement risk data to obtain an adaptability evaluation result.

[0030] In this solution, if the adaptability of the initial design solution of the pile position is less than the adaptability threshold, the initial design solution of the pile position is optimized based on the genetic algorithm to obtain the optimized design solution of the pile position, which is specifically:

[0031] Obtain the pile foundation settlement risk control requirements of the target project, and determine the adaptability threshold of the pile position design scheme according to the risk control requirements;

[0032] According to the adaptability evaluation result, if the adaptability of the initial design scheme of the pile position is less than the adaptability threshold, a genetic algorithm is introduced to convert the initial design scheme of the pile position into a binary representation, and a number of initial design schemes are randomly generated according to the genetic algorithm as population individuals of the genetic algorithm, each population individual represents a possible pile position design scheme;

[0033] Simulate and construct each population individual in the three-dimensional geological structure model, and update the geological parameters of the pile foundation settlement simulation model. According to the updated pile foundation settlement simulation model, conduct settlement risk assessment for each population individual and determine the adaptability of each population individual.

[0034] Based on the roulette wheel selection method, individuals of the population with fitness greater than the preset value are selected as the parent generation, and the selected parent generation is subjected to a multi-point crossover operation to generate new individuals, and the new individuals are subjected to a mutation operation to obtain a new generation of population;

[0035] The individuals in the new generation population are evaluated for their adaptability again, and parent selection, crossover and mutation iteration operations are performed until the adaptability of the population is greater than the adaptability threshold, and the population individuals are output. The initial design scheme of the pile position is optimized according to the output population individuals to obtain the optimized pile position design scheme.

[0036] In this solution, the pile foundation construction is carried out according to the pile position design optimization solution, the surface stress change data of the pile foundation is monitored in real time, and the stress change in the future preset time period is predicted according to the surface stress change data of the pile foundation to obtain the stress change prediction result, which is specifically:

[0037] Perform actual pile foundation construction according to the pile position design optimization scheme, and monitor the surface stress change data of the pile foundation in real time based on the stress sensor;

[0038] The surface of the pile foundation is divided into a plurality of square grids, the position information of the stress sensor is obtained, and an interpolation operation is performed on each square grid based on a spatial interpolation method and the position information of the stress sensor to obtain stress change data of each square grid;

[0039] Sorting the stress change data of each square grid according to the time series to obtain stress change time series data;

[0040] Building a stress change prediction model based on the LSTM algorithm, dividing the stress change time series data into training set data and prediction set data according to a preset ratio, and importing the training set data into the stress change prediction model for model training;

[0041] The prediction set data is imported into the trained model to predict the stress change on the pile foundation surface within a future preset time period to obtain the stress change prediction result.

[0042] In this solution, the uniformity of the stress distribution on the pile foundation surface at each time point in the future preset time period is evaluated according to the stress change prediction result, and the evaluation result of the uniformity of the stress distribution on the pile foundation surface is obtained, which is specifically:

[0043] Visualizing the pile foundation surface stress at each time point within a preset time period according to the stress change prediction result to obtain a schematic diagram of the pile foundation surface stress at each time point;

[0044] Converting the pile foundation surface stress schematic diagram at each time point into a thermal diagram to obtain a pile foundation surface stress thermal diagram at each time point;

[0045] Calculating a color histogram of the pile foundation surface stress thermodynamic map, and obtaining a color value of each square grid according to the color histogram;

[0046] Performing a clustering operation on the color values ​​based on a clustering algorithm to obtain a clustering result, and determining a clustering ratio and a color distribution area of ​​each color of the pile foundation surface stress thermodynamic map according to the clustering result;

[0047] The pile foundation surface stress distribution is determined according to the clustering ratio and the color distribution area, and the uniformity of the pile foundation surface stress at each time point is evaluated according to the pile foundation surface stress distribution to obtain a pile foundation surface stress distribution uniformity evaluation result.

[0048] In this solution, the pile foundation design and construction solution is determined based on the stress distribution uniformity evaluation result on the pile foundation surface, specifically:

[0049] According to the pile foundation surface stress distribution uniformity evaluation result, the pile foundation surface stress schematic diagram whose pile foundation surface stress uniformity is lower than a preset value is marked to obtain a marked pile foundation surface stress schematic diagram;

[0050] Obtain the acquisition time point data of each marked pile foundation surface stress schematic diagram, mark the time point when the pile foundation surface stress uniformity begins to be lower than the preset value, and mark it as the pile foundation to be fixed time point;

[0051] Determine, according to the pile foundation surface stress distribution uniformity evaluation result, an area where the pile foundation surface uniformity is lower than a second preset value, and mark the area as a stress change area;

[0052] Analyze the stress change area. If symmetrical stress change areas appear on the surface of the pile foundation, and the stress in one of the symmetrical stress change areas increases while the stress in the other stress change area decreases, the pile foundation is marked as a pile foundation with lateral tilt risk.

[0053] At the time node when the pile foundation is to be fixed, a lateral support pile is added to the pile foundation with a risk of lateral tilt, and the installation position of the lateral support pile is determined according to the stress change area, and the severity of the stress change is determined according to the stress change prediction result of the stress change area in a future preset time period, and the diameter of the lateral support pile is determined according to the severity, so as to obtain a first fixing scheme for the pile foundation;

[0054] According to the pile foundation surface stress distribution uniformity assessment result and stress change prediction result, if the pile foundation surface stress distribution uniformity is greater than a preset value but stress changes occur, the pile foundation is marked as a settlement risk pile foundation, and the time point when the stress change is greater than the preset stress change value is marked and calibrated as a fixed time point for pile foundation anti-settlement;

[0055] At the fixed time point of pile foundation anti-settlement, longitudinal auxiliary piles are added to the settlement risk pile foundation, and the settlement severity is determined according to the predicted result of stress change of the settlement risk pile foundation in a future preset time period, and the number of longitudinal auxiliary piles to be added is determined according to the settlement severity to obtain a second fixing scheme for the pile foundation, and the first fixing scheme and the second fixing scheme are integrated to obtain a pile foundation design and construction scheme.

[0056] The second aspect of the present invention further provides a system for automatic optimization of pile positions in deep soft soil, the system comprising: a memory and a processor, the memory comprising a method program for automatic optimization of pile positions in deep soft soil, and when the method program for automatic optimization of pile positions in deep soft soil is executed by the processor, the following steps are implemented:

[0057] Obtaining pile foundation design drawing data of the target project, and determining an initial design scheme for pile positions of the target project according to the design drawing data;

[0058] Acquire geological parameters of the target engineering construction location, and perform adaptability evaluation on the initial design scheme of the pile position according to the geological parameters to obtain adaptability evaluation results;

[0059] If the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on a genetic algorithm to obtain an optimized pile position design scheme;

[0060] Perform pile foundation construction according to the pile position design optimization plan, monitor the pile foundation surface stress change data in real time, predict the stress change in a future preset time period according to the pile foundation surface stress change data, and obtain the stress change prediction result;

[0061] Evaluate the uniformity of the stress distribution on the pile foundation surface at each time point in a future preset time period according to the stress change prediction result, and obtain an evaluation result of the uniformity of the stress distribution on the pile foundation surface;

[0062] The pile foundation design and construction plan are determined based on the pile foundation surface stress distribution uniformity assessment results.

[0063] The present invention discloses a method and system for automatic optimization of pile positions suitable for thick soft soil. The method comprises: obtaining the design drawing data of the pile foundation of the construction project, determining the initial design scheme of the pile position; evaluating the adaptability of the initial design scheme according to the geological parameters of the construction location, and if the adaptability is less than the threshold, optimizing based on the genetic algorithm to generate an optimization scheme; constructing the pile foundation according to the optimization scheme, and monitoring the stress changes on the pile foundation surface in real time, predicting the future stress changes and evaluating the uniformity of the stress distribution; and finally determining the pile foundation design and construction scheme according to the evaluation results. The method improves the adaptability and safety of pile foundation design and construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart of a method for automatically optimizing pile positions in thick soft soil according to the present invention is shown;

[0065] Figure 2 A flow chart showing a pile position design optimization scheme obtained by the present invention is shown;

[0066] Figure 3 A flow chart showing the stress change prediction result obtained by the present invention is shown;

[0067] Figure 4 A block diagram of a system for automatically optimizing pile positions in thick soft soil according to the present invention is shown. DETAILED DESCRIPTION

[0068] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0070] Figure 1 The flowchart of the method for automatic optimization of pile position applicable to thick soft soil of the present invention is shown.

[0071] like Figure 1 As shown, the first aspect of the present invention provides a method for automatic optimization of pile positions applicable to thick soft soil, comprising:

[0072] S102, obtaining pile foundation design drawing data of the target project, and determining an initial design scheme of the pile position of the target project according to the design drawing data;

[0073] S104, obtaining geological parameters of the target engineering construction location, and performing adaptability evaluation on the initial design scheme of the pile position according to the geological parameters to obtain adaptability evaluation results;

[0074] S106, if the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on a genetic algorithm to obtain an optimized pile position design scheme;

[0075] S108, performing pile foundation construction according to the pile position design optimization scheme, monitoring the pile foundation surface stress change data in real time, predicting the stress change in a future preset time period according to the pile foundation surface stress change data, and obtaining a stress change prediction result;

[0076] S110, evaluating the uniformity of stress distribution on the pile foundation surface at each time point in a future preset time period according to the stress change prediction result, and obtaining a result of evaluating the uniformity of stress distribution on the pile foundation surface;

[0077] S112, determining a pile foundation design and construction plan according to the pile foundation surface stress distribution uniformity evaluation result.

[0078] It should be noted that by obtaining the geological parameters of the target project and evaluating the adaptability of the initial design scheme of the pile position in combination with the pile foundation design drawings, the adaptability of the design scheme under specific geological conditions can be identified, that is, whether the design scheme can meet the requirements of bearing capacity and settlement. When the adaptability of the initial design scheme is lower than the threshold, it can be optimized by genetic algorithm to avoid the safety hazards caused by unreasonable pile position design and improve the safety of pile foundation design; genetic algorithm is a global search algorithm with good global optimization ability and robustness, and can dynamically optimize the pile position design scheme under various complex geological conditions. Generate multiple pile position design schemes through genetic algorithm, and iterate continuously according to the adaptability evaluation results, which can effectively deal with uncertain factors such as complex geological structure and large differences in soil bearing capacity, and finally obtain a pile position design optimization scheme that is more adapted to actual geological conditions; by real-time monitoring of the stress change data on the pile foundation surface, predict the stress change in the future preset time period, and identify potential stress concentration or stress unevenness in advance; the stress change prediction model can be dynamically updated according to the real-time monitoring data, so that the pile foundation design and construction plan can respond to sudden situations such as geological changes and load changes in a timely manner. By adjusting the fixed plan in real time, such as adjusting the position of supporting piles, adding or reducing auxiliary piles, etc., it is possible to flexibly respond to uncertainties in the construction process, reduce unexpected situations that may occur during pile foundation construction, and improve the adaptability and emergency response capabilities of the project; the target projects include construction projects and port construction projects.

[0079] According to an embodiment of the present invention, the obtaining of the pile foundation design drawing data of the target project and determining the initial design scheme of the pile position of the target project according to the design drawing data are specifically as follows:

[0080] Acquire the pile foundation design drawing data of the target project, convert the pile foundation design drawing data into an electronic image, and obtain an electronic design drawing;

[0081] Obtaining a legend of the pile foundation design drawing, marking the legend with corresponding component names, and obtaining a name-marked legend;

[0082] A pile foundation recognition model is constructed based on a convolutional neural network, an input layer, a convolutional layer, an activation function, a pooling layer, a fully connected layer, and an output layer of the pile foundation recognition model are set, and a name annotation legend is imported into the pile foundation recognition model for model training;

[0083] The electronic design drawing is imported into the trained pile foundation recognition model to perform pile foundation recognition, and an initial design scheme of pile positions of the target project is determined according to the recognition result. The initial design scheme of pile positions includes the number of pile foundations, pile foundation diameter and length, and pile foundation position.

[0084] It should be noted that by automatically identifying electronic design drawings through convolutional neural networks, key information in pile foundation design drawings can be quickly extracted, such as the number, diameter, length, location, etc. of pile foundations. This automated recognition process can greatly reduce manual operation time, avoid errors caused by manual marking and recognition, and significantly improve recognition efficiency.

[0085] According to an embodiment of the present invention, the geological parameters of the target engineering construction location are obtained, and the adaptability of the initial design scheme of the pile position is evaluated according to the geological parameters to obtain the adaptability evaluation result, which is specifically:

[0086] Obtaining geological parameters of the target engineering construction location, including soil type, distribution, thickness, density, porosity, and water content of each soil layer;

[0087] Constructing a three-dimensional model of the geological structure of the target engineering construction location according to the geological parameters, and constructing a three-dimensional model of the pile foundation according to the initial design plan of the pile position;

[0088] According to the pile position initial design scheme, the pile foundation three-dimensional model is simulated and constructed in the geological structure three-dimensional model to obtain a simulated three-dimensional model;

[0089] Obtaining the relationship data of the impact of compression on the soft soil geological parameters of each soil layer, adjusting the geological parameters of the target engineering construction location after simulation and construction according to the relationship data of the impact of the change, and obtaining the geological update parameters;

[0090] Based on the finite element analysis method, the soil layer in the simulated three-dimensional model is divided into N finite element grids according to the preset size, and the geological update parameters are mapped to each finite element grid;

[0091] Obtaining pile foundation surface roughness data, calculating and determining the load capacity data of each finite element grid for the pile foundation according to the geological update parameters and the pile foundation surface roughness data, and constructing a pile foundation settlement simulation model according to the load capacity data of each finite element grid for the pile foundation;

[0092] Constructing a settlement numerical simulation model based on the bearing capacity data of the pile foundation of each finite element grid, obtaining the bearing capacity data of the soil layer at the construction location of the target project for the target project and the minimum bearing capacity data of the soil layer required for constructing the target project;

[0093] Calculating the required bearing capacity of the pile foundation for the target project based on the bearing capacity data of the soil layer for the target project and the minimum bearing capacity data of the soil layer required for constructing the target project;

[0094] Calculating the minimum bearing capacity of each pile foundation in the target project according to the required bearing capacity of the pile foundation for the target project, applying the minimum bearing capacity of each pile foundation to each pile foundation in the target project according to the pile foundation settlement simulation model, evaluating the settlement risk of each pile foundation, and obtaining settlement risk data;

[0095] The adaptability of the initial design scheme of the pile position in the soil layer of the construction location of the target project is evaluated based on the settlement risk data to obtain an adaptability evaluation result.

[0096] It should be noted that by establishing a simulated three-dimensional model, the finite element analysis method can discretize the constructed three-dimensional model into a finite number of finite elements. Each finite element is represented by a simple geometric shape (such as a triangle or a tetrahedron), and these finite elements together constitute the entire calculation model. The discretization process converts continuous physical problems into discrete numerical problems and sets the boundary conditions of the model to simulate fixed, free or sliding boundaries in actual engineering. The boundary conditions ensure that the model can reflect the real structural behavior during the calculation process and apply actual loads, such as the weight of the building, seismic loads, etc. These loads will act on the pile foundation and soil layer, affecting their settlement and deformation; the finite element method solves the displacement, stress and strain in the model by solving a system of linear equations. The finite element method divides the complex continuum into multiple finite element grids, and can perform detailed analysis of stress and strain in each grid. For the interaction between pile foundation and soft soil, this refined mechanical simulation can accurately capture the distribution and transmission laws of stress in geological structures, thereby more accurately simulating the settlement behavior of pile foundations in different soil layers. The adaptability is that the higher the settlement risk, the lower the adaptability.

[0097] Figure 2 A flow chart of the pile position design optimization scheme obtained in the present invention is shown.

[0098] According to an embodiment of the present invention, if the adaptability of the initial design scheme of the pile position is less than the adaptability threshold, the initial design scheme of the pile position is optimized based on a genetic algorithm to obtain an optimized pile position design scheme, specifically:

[0099] S202, obtaining the risk control requirements for pile foundation settlement of the target project, and determining the adaptability threshold of the pile position design scheme according to the risk control requirements;

[0100] S204, according to the adaptability evaluation result, if the adaptability of the initial pile position design scheme is less than the adaptability threshold, introduce a genetic algorithm to convert the initial pile position design scheme into a binary representation, and randomly generate a number of initial design schemes according to the genetic algorithm as population individuals of the genetic algorithm, each population individual represents a possible pile position design scheme;

[0101] S206, simulating and constructing each population individual in the three-dimensional geological structure model, and updating the geological parameters of the pile foundation settlement simulation model, performing settlement risk assessment on each population individual according to the updated pile foundation settlement simulation model, and determining the adaptability of each population individual;

[0102] S208, selecting a population individual with an adaptability greater than a preset value as a parent generation based on a roulette wheel selection method, performing a multi-point crossover operation on the selected parent generation to generate a new individual, performing a mutation operation on the new individual, and obtaining a new generation of population;

[0103] S210, re-evaluate the adaptability of individuals in the new generation population, and perform parent selection, crossover and mutation iteration operations until the adaptability of the population is greater than the adaptability threshold, output the population individuals, and optimize the initial design scheme of the pile position according to the output population individuals to obtain the pile position design optimization scheme.

[0104] It should be noted that when the adaptability of the initial design scheme of the pile position is less than the adaptability threshold, it is considered that the risk of pile foundation settlement after the pile foundation construction is carried out according to the initial design scheme of the pile position is high, and the pile foundation design requirements of the target project cannot be met. Therefore, the initial design scheme of the pile position is optimized by the genetic algorithm. First, the pile position design scheme is converted into a binary coding form suitable for genetic algorithm processing, and each individual (design scheme) is represented by a binary string. During initialization, multiple design schemes are randomly generated as the initial population. Next, the settlement numerical simulation model is used to evaluate the pros and cons of each individual. During the evaluation process, individuals with high fitness represent better performance designs. Then, the selection mechanism is used to select individuals with higher fitness from the current population as parents, and the excellent genes of these individuals are passed on to the next generation through roulette selection. The crossover operation simulates gene recombination, exchanges the genes of the parent individuals to generate new offspring individuals, and introduces new gene mutations through mutation operations to increase the diversity of the population. Iterate the selection, crossover and mutation operations to continuously optimize the overall fitness of the population. After multiple generations of genetic operations, the final output design solutions are usually optimal or near-optimal pile position design solutions, which can effectively meet the design requirements, reduce settlement risks and improve bearing capacity, thereby providing an optimized design basis for actual engineering implementation.

[0105] Figure 3 A flow chart of the present invention for obtaining stress change prediction results is shown.

[0106] According to an embodiment of the present invention, the pile foundation construction is carried out according to the pile position design optimization scheme, the surface stress change data of the pile foundation is monitored in real time, and the stress change in a future preset time period is predicted according to the surface stress change data of the pile foundation to obtain the stress change prediction result, which is specifically:

[0107] S302, performing actual pile foundation construction according to the pile position design optimization scheme, and monitoring the surface stress change data of the pile foundation in real time based on the stress sensor;

[0108] S304, dividing the pile foundation surface into a plurality of square grids, obtaining position information of the stress sensor, and performing an interpolation operation on each square grid based on a spatial interpolation method and the position information of the stress sensor to obtain stress change data of each square grid;

[0109] S306, sorting the stress change data of each square grid according to the time series to obtain stress change time series data;

[0110] S308, constructing a stress change prediction model based on the LSTM algorithm, dividing the stress change time series data into training set data and prediction set data according to a preset ratio, and importing the training set data into the stress change prediction model for model training;

[0111] S310, importing the prediction set data into the trained model to predict the stress change on the pile foundation surface within a future preset time period to obtain a stress change prediction result.

[0112] It should be noted that the LSTM algorithm can effectively capture long-term dependencies in time series data, which is particularly important for situations such as stress changes that change dynamically over time. By using real-time monitored stress data as input, the LSTM model can learn and understand the temporal pattern of stress changes, thereby accurately predicting future stress trends. This predictive capability enables engineers to identify potential stress anomalies or risks in advance and take preventive measures to ensure structural safety. Secondly, LSTM-based predictions can provide detailed information about the stress distribution on the surface of the pile foundation, allowing the design and construction team to better understand the uneven stress distribution that may occur during the construction process. This allows timely adjustments to be made during the construction process to optimize the stability and bearing capacity of the pile foundation. In addition, accurate stress change predictions can also optimize resource allocation, reduce over-construction or unnecessary correction work, thereby improving construction efficiency and reducing costs.

[0113] According to an embodiment of the present invention, the uniformity of the stress distribution on the pile foundation surface at each time point in a future preset time period is evaluated according to the stress change prediction result, and the evaluation result of the uniformity of the stress distribution on the pile foundation surface is obtained, which is specifically:

[0114] Visualizing the pile foundation surface stress at each time point within a preset time period according to the stress change prediction result to obtain a schematic diagram of the pile foundation surface stress at each time point;

[0115] Converting the pile foundation surface stress schematic diagram at each time point into a thermal diagram to obtain a pile foundation surface stress thermal diagram at each time point;

[0116] Calculating a color histogram of the pile foundation surface stress thermodynamic map, and obtaining a color value of each square grid according to the color histogram;

[0117] Performing a clustering operation on the color values ​​based on a clustering algorithm to obtain a clustering result, and determining a clustering ratio and a color distribution area of ​​each color of the pile foundation surface stress thermodynamic map according to the clustering result;

[0118] The pile foundation surface stress distribution is determined according to the clustering ratio and the color distribution area, and the uniformity of the pile foundation surface stress at each time point is evaluated according to the pile foundation surface stress distribution to obtain a pile foundation surface stress distribution uniformity evaluation result.

[0119] It should be noted that the stress data on the pile foundation surface monitored in real time is visualized and converted into an image form. This usually includes mapping the data points onto a grid on the pile foundation surface and representing different stress values ​​in a color-coded manner. These color-coded images are called stress diagrams. The stress diagrams are further processed to generate a heat map. The heat map represents the distribution of data values ​​through color gradients, which can intuitively show the stress intensity in different areas of the pile foundation surface. Different colors represent different stress values, making the high and low stress distribution clear at a glance. The color information is extracted from the heat map to generate a color histogram. The color histogram is a statistical representation of the frequency of occurrence of each color in the heat map, which helps analyze the concentration and regional characteristics of the stress distribution. The color values ​​in the color histogram are analyzed using a clustering algorithm. The clustering algorithm can classify the color values ​​into several categories and identify the pattern of stress distribution. In this way, the areas of stress distribution on the pile foundation surface can be classified and identified, such as high stress areas and low stress areas. Based on the clustering results, the uniformity of stress distribution at each time point is calculated. This involves evaluating the proportions and distribution of the different colored areas to determine the uniformity or inhomogeneity of the stress.

[0120] According to an embodiment of the present invention, the pile foundation design and construction scheme is determined according to the pile foundation surface stress distribution uniformity evaluation result, specifically:

[0121] According to the pile foundation surface stress distribution uniformity evaluation result, the pile foundation surface stress schematic diagram whose pile foundation surface stress uniformity is lower than a preset value is marked to obtain a marked pile foundation surface stress schematic diagram;

[0122] Obtain the acquisition time point data of each marked pile foundation surface stress schematic diagram, mark the time point when the pile foundation surface stress uniformity begins to be lower than the preset value, and mark it as the pile foundation to be fixed time point;

[0123] Determine, according to the pile foundation surface stress distribution uniformity evaluation result, an area where the pile foundation surface uniformity is lower than a second preset value, and mark the area as a stress change area;

[0124] Analyze the stress change area. If symmetrical stress change areas appear on the surface of the pile foundation, and the stress in one of the symmetrical stress change areas increases while the stress in the other stress change area decreases, the pile foundation is marked as a pile foundation with lateral tilt risk.

[0125] At the time node when the pile foundation is to be fixed, a lateral support pile is added to the pile foundation with a risk of lateral tilt, and the installation position of the lateral support pile is determined according to the stress change area, and the severity of the stress change is determined according to the stress change prediction result of the stress change area in a future preset time period, and the diameter of the lateral support pile is determined according to the severity, so as to obtain a first fixing scheme for the pile foundation;

[0126] It should be noted that the pile foundation surface stress schematic diagram where the pile foundation surface stress uniformity is lower than the preset value is marked. The pile foundation surface stress uniformity lower than the preset value indicates that the pile foundation has a stress concentration area, which may cause the pile foundation to tilt laterally. Therefore, according to the pile foundation surface stress distribution uniformity assessment result, those areas where the stress uniformity is lower than the preset value are identified. The stress distribution in these areas is uneven, and there may be potential structural problems. These areas are marked on the pile foundation surface stress schematic diagram to form a marked pile foundation surface stress schematic diagram. The acquisition time point data of each marked pile foundation surface stress schematic diagram is obtained, and the time point when the stress uniformity begins to be lower than the preset value is calibrated, which is called the pile foundation to be fixed time point. These time points mark the critical moments that occur during the construction process, and measures need to be taken to intervene. According to the pile foundation surface stress distribution uniformity assessment result, those areas where the stress uniformity is lower than the second preset value are determined. These areas are marked as stress change areas, which show large stress fluctuations or uneven distribution. The stress change areas are analyzed in detail to check whether there are symmetrical stress change areas. In particular, if the stress in one area of ​​the symmetrical stress change area increases and the stress in another area decreases, this symmetrical change may lead to the risk of lateral tilting of the pile foundation. If this situation exists, the pile foundation is marked as a pile foundation with a risk of lateral tilting. At the time when the pile foundation is to be fixed, lateral support piles are added to the pile foundation marked as a risk of lateral tilting. The installation location of the lateral support piles is selected based on the distribution of the stress change area, and the severity of the stress change is determined based on the predicted results of the stress change in the future preset time period. This information helps determine the diameter of the lateral support pile to provide sufficient support. The final solution is the first fixation solution for the pile foundation.

[0127] According to the pile foundation surface stress distribution uniformity assessment result and stress change prediction result, if the pile foundation surface stress distribution uniformity is greater than a preset value but stress changes occur, the pile foundation is marked as a settlement risk pile foundation, and the time point when the stress change is greater than the preset stress change value is marked and calibrated as a fixed time point for pile foundation anti-settlement;

[0128] At the fixed time point of pile foundation anti-settlement, longitudinal auxiliary piles are added to the settlement risk pile foundation, and the settlement severity is determined according to the predicted result of stress change of the settlement risk pile foundation in a future preset time period, and the number of longitudinal auxiliary piles to be added is determined according to the settlement severity to obtain a second fixing scheme for the pile foundation, and the first fixing scheme and the second fixing scheme are integrated to obtain a pile foundation design and construction scheme.

[0129] It should be noted that when the pile foundation settles, the stress on the pile foundation surface is evenly distributed during the settlement process, but the surface stress will decrease, resulting in the deep soft soil layer acting insufficiently on the pile foundation to prevent the pile foundation from settling. Therefore, according to the evaluation results of the uniformity of the pile foundation surface stress distribution, if the uniformity of the pile foundation surface stress distribution is greater than the preset value, but stress changes are found, these pile foundations are marked as settlement risk pile foundations. This means that although the overall stress distribution is relatively uniform, the pile foundation as a whole has experienced fluctuations that exceed the preset stress change value, indicating that settlement problems may occur. On the settlement risk pile foundation, the specific time points at which the stress change is greater than the preset stress change value are determined. These time points are marked as fixed time points for pile foundation anti-settlement, which means that additional measures should be taken at these moments to deal with possible settlement. At the determined fixed time points for pile foundation anti-settlement, the settlement risk pile foundation is intervened and longitudinal auxiliary piles are added. This step aims to enhance the stability of the pile foundation through additional longitudinal support and reduce or prevent the occurrence of settlement. The number and location of the additional longitudinal auxiliary piles are determined according to the specific situation of the settlement risk. Based on the predicted results of stress changes in the future preset time period of the settlement risk pile foundation, the severity of the settlement is evaluated. By analyzing the trend and amplitude of stress changes in the predicted results, the degree of settlement that the pile foundation may experience is determined. According to the assessed settlement severity, the number of longitudinal auxiliary piles that need to be added is calculated. When the severity is high, more auxiliary piles may need to be added to ensure the stability of the pile foundation. This calculation takes into account the predicted results of future stress changes to ensure that possible settlement risks can be dealt with. The results of the above steps are integrated to obtain the second fixing scheme for the pile foundation, and the first fixing scheme and the second fixing scheme are integrated to obtain the pile foundation design and construction plan. This plan includes specific operations performed at the anti-settlement fixing time point, such as the number and installation location of the increased longitudinal auxiliary piles, aiming to effectively reduce and control the settlement risk.

[0130] Figure 4 A block diagram of a system for automatically optimizing pile positions in thick soft soil according to the present invention is shown.

[0131] The second aspect of the present invention further provides a system 4 for automatic optimization of pile positions in deep soft soil, the system comprising: a memory 41 and a processor 42, wherein the memory comprises a method program for automatic optimization of pile positions in deep soft soil, and when the method program for automatic optimization of pile positions in deep soft soil is executed by the processor, the following steps are implemented:

[0132] Obtaining pile foundation design drawing data of the target project, and determining an initial design scheme for pile positions of the target project according to the design drawing data;

[0133] Acquire geological parameters of the target engineering construction location, and perform adaptability evaluation on the initial design scheme of the pile position according to the geological parameters to obtain adaptability evaluation results;

[0134] If the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on a genetic algorithm to obtain an optimized pile position design scheme;

[0135] Perform pile foundation construction according to the pile position design optimization plan, monitor the pile foundation surface stress change data in real time, predict the stress change in a future preset time period according to the pile foundation surface stress change data, and obtain the stress change prediction result;

[0136] Evaluate the uniformity of the stress distribution on the pile foundation surface at each time point in a future preset time period according to the stress change prediction result, and obtain an evaluation result of the uniformity of the stress distribution on the pile foundation surface;

[0137] The pile foundation design and construction plan are determined based on the pile foundation surface stress distribution uniformity assessment results.

[0138] The present invention discloses a method and system for automatic optimization of pile positions suitable for thick soft soil. The method comprises: obtaining the design drawing data of the pile foundation of the construction project, determining the initial design scheme of the pile position; evaluating the adaptability of the initial design scheme according to the geological parameters of the construction location, and if the adaptability is less than the threshold, optimizing based on the genetic algorithm to generate an optimization scheme; constructing the pile foundation according to the optimization scheme, and monitoring the stress changes on the pile foundation surface in real time, predicting the future stress changes and evaluating the uniformity of the stress distribution; and finally determining the pile foundation design and construction scheme according to the evaluation results. The method improves the adaptability and safety of pile foundation design and construction.

[0139] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0140] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0141] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0142] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0143] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0144] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for automatic optimization of pile position suitable for thick soft soil, characterized in that: The following steps are involved: Obtaining pile foundation design drawing data of the target project, and determining an initial design scheme for pile positions of the target project according to the design drawing data; Acquire geological parameters of the target engineering construction location, and perform adaptability evaluation on the initial design scheme of the pile position according to the geological parameters to obtain adaptability evaluation results; If the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on a genetic algorithm to obtain an optimized pile position design scheme; Perform pile foundation construction according to the pile position design optimization plan, monitor the pile foundation surface stress change data in real time, predict the stress change in a future preset time period according to the pile foundation surface stress change data, and obtain the stress change prediction result; Evaluate the uniformity of the stress distribution on the pile foundation surface at each time point in a future preset time period according to the stress change prediction result, and obtain an evaluation result of the uniformity of the stress distribution on the pile foundation surface; Determining the pile foundation design and construction plan based on the pile foundation surface stress distribution uniformity assessment result; The uniformity of the stress distribution on the pile foundation surface at each time point in the future preset time period is evaluated according to the stress change prediction result, and the uniformity evaluation result of the stress distribution on the pile foundation surface is obtained, which is specifically: Visualizing the pile foundation surface stress at each time point within a preset time period according to the stress change prediction result to obtain a schematic diagram of the pile foundation surface stress at each time point; Converting the pile foundation surface stress schematic diagram at each time point into a thermal diagram to obtain a pile foundation surface stress thermal diagram at each time point; Calculating a color histogram of the pile foundation surface stress thermodynamic map, and obtaining a color value of each square grid according to the color histogram; Performing a clustering operation on the color values ​​based on a clustering algorithm to obtain a clustering result, and determining a clustering ratio and a color distribution area of ​​each color of the pile foundation surface stress thermodynamic map according to the clustering result; The pile foundation surface stress distribution is determined according to the clustering ratio and the color distribution area, and the uniformity of the pile foundation surface stress at each time point is evaluated according to the pile foundation surface stress distribution to obtain a pile foundation surface stress distribution uniformity evaluation result.

2. The method for automatic optimization of pile position applicable to deep soft soil according to claim 1, characterized in that: The method of obtaining the pile foundation design drawing data of the target project and determining the initial design scheme of the pile position of the target project according to the design drawing data is specifically as follows: Acquire the pile foundation design drawing data of the target project, convert the pile foundation design drawing data into an electronic image, and obtain an electronic design drawing; Obtaining a legend of the pile foundation design drawing, marking the legend with corresponding component names, and obtaining a name-marked legend; A pile foundation recognition model is constructed based on a convolutional neural network, an input layer, a convolutional layer, an activation function, a pooling layer, a fully connected layer, and an output layer of the pile foundation recognition model are set, and a name annotation legend is imported into the pile foundation recognition model for model training; The electronic design drawing is imported into the trained pile foundation recognition model to perform pile foundation recognition, and an initial design scheme of pile positions of the target project is determined according to the recognition result. The initial design scheme of pile positions includes the number of pile foundations, pile foundation diameter and length, and pile foundation position.

3. The method for automatic optimization of pile position applicable to deep soft soil according to claim 1, characterized in that: The geological parameters of the target engineering construction location are obtained, and the adaptability of the initial design scheme of the pile position is evaluated according to the geological parameters to obtain the adaptability evaluation result, which is specifically: Obtaining geological parameters of the target engineering construction location, the geological parameters including soil type, distribution, thickness, density, porosity, and water content of each soil layer; Constructing a three-dimensional model of the geological structure of the target engineering construction location according to the geological parameters, and constructing a three-dimensional model of the pile foundation according to the initial design plan of the pile position; According to the pile position initial design scheme, the pile foundation three-dimensional model is simulated and constructed in the geological structure three-dimensional model to obtain a simulated three-dimensional model; Obtaining the relationship data of the impact of compression on the soft soil geological parameters of each soil layer, adjusting the geological parameters of the target engineering construction location after simulation and construction according to the relationship data of the impact of the change, and obtaining the geological update parameters; Based on the finite element analysis method, the soil layer in the simulated three-dimensional model is divided into N finite element grids according to the preset size, and the geological update parameters are mapped to each finite element grid; Obtaining pile foundation surface roughness data, calculating and determining the load capacity data of each finite element grid for the pile foundation according to the geological update parameters and the pile foundation surface roughness data, and constructing a pile foundation settlement simulation model according to the load capacity data of each finite element grid for the pile foundation; Constructing a settlement numerical simulation model based on the bearing capacity data of the pile foundation of each finite element grid, obtaining the bearing capacity data of the soil layer at the construction location of the target project for the target project and the minimum bearing capacity data of the soil layer required for constructing the target project; Calculating the required bearing capacity of the pile foundation for the target project based on the bearing capacity data of the soil layer for the target project and the minimum bearing capacity data of the soil layer required for constructing the target project; Calculating the minimum bearing capacity of each pile foundation in the target project according to the required bearing capacity of the pile foundation for the target project, applying the minimum bearing capacity of each pile foundation to each pile foundation in the target project according to the pile foundation settlement simulation model, evaluating the settlement risk of each pile foundation, and obtaining settlement risk data; The adaptability of the initial design scheme of the pile position in the soil layer at the construction location of the target project is evaluated based on the settlement risk data to obtain an adaptability evaluation result.

4. The method for automatic optimization of pile position applicable to deep soft soil according to claim 3, characterized in that: If the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on the genetic algorithm to obtain the pile position design optimization scheme, which is specifically: Obtain the pile foundation settlement risk control requirements of the target project, and determine the adaptability threshold of the pile position design scheme according to the risk control requirements; According to the adaptability evaluation result, if the adaptability of the initial design scheme of the pile position is less than the adaptability threshold, a genetic algorithm is introduced to convert the initial design scheme of the pile position into a binary representation, and a number of initial design schemes are randomly generated according to the genetic algorithm as population individuals of the genetic algorithm, each population individual represents a possible pile position design scheme; Simulate and construct each population individual in the three-dimensional geological structure model, and update the geological parameters of the pile foundation settlement simulation model. According to the updated pile foundation settlement simulation model, conduct settlement risk assessment for each population individual and determine the adaptability of each population individual. Based on the roulette wheel selection method, individuals of the population with fitness greater than the preset value are selected as the parent generation, and the selected parent generation is subjected to a multi-point crossover operation to generate new individuals, and the new individuals are subjected to a mutation operation to obtain a new generation of population; The individuals in the new generation population are evaluated for their adaptability again, and parent selection, crossover and mutation iteration operations are performed until the adaptability of the population is greater than the adaptability threshold, and the population individuals are output. The initial design scheme of the pile position is optimized according to the output population individuals to obtain the optimized pile position design scheme.

5. The method for automatic optimization of pile position applicable to thick soft soil according to claim 1, characterized in that: The pile foundation construction is performed according to the pile position design optimization scheme, the surface stress change data of the pile foundation is monitored in real time, and the stress change in a future preset time period is predicted according to the surface stress change data of the pile foundation to obtain the stress change prediction result, specifically: Perform actual pile foundation construction according to the pile position design optimization scheme, and monitor the surface stress change data of the pile foundation in real time based on the stress sensor; The surface of the pile foundation is divided into a plurality of square grids, the position information of the stress sensor is obtained, and an interpolation operation is performed on each square grid based on a spatial interpolation method and the position information of the stress sensor to obtain stress change data of each square grid; Sorting the stress change data of each square grid according to the time series to obtain stress change time series data; Building a stress change prediction model based on the LSTM algorithm, dividing the stress change time series data into training set data and prediction set data according to a preset ratio, and importing the training set data into the stress change prediction model for model training; The prediction set data is imported into the trained model to predict the stress change on the pile foundation surface within a future preset time period to obtain the stress change prediction result.

6. The method for automatic optimization of pile position applicable to thick soft soil according to claim 1, characterized in that: The pile foundation design and construction plan are determined according to the pile foundation surface stress distribution uniformity evaluation result, specifically: According to the pile foundation surface stress distribution uniformity evaluation result, the pile foundation surface stress schematic diagram whose pile foundation surface stress uniformity is lower than a preset value is marked to obtain a marked pile foundation surface stress schematic diagram; Obtain the acquisition time point data of each marked pile foundation surface stress schematic diagram, mark the time point when the pile foundation surface stress uniformity begins to be lower than the preset value, and mark it as the pile foundation to be fixed time point; Determine, according to the pile foundation surface stress distribution uniformity evaluation result, an area where the pile foundation surface uniformity is lower than a second preset value, and mark the area as a stress change area; Analyze the stress change area. If symmetrical stress change areas appear on the surface of the pile foundation, and the stress in one of the symmetrical stress change areas increases while the stress in the other stress change area decreases, the pile foundation is marked as a pile foundation with lateral tilt risk. At the time node when the pile foundation is to be fixed, a lateral support pile is added to the pile foundation with a risk of lateral tilt, and the installation position of the lateral support pile is determined according to the stress change area, and the severity of the stress change is determined according to the stress change prediction result of the stress change area in a future preset time period, and the diameter of the lateral support pile is determined according to the severity, so as to obtain a first fixing scheme for the pile foundation; According to the pile foundation surface stress distribution uniformity assessment result and stress change prediction result, if the pile foundation surface stress distribution uniformity is greater than a preset value but stress changes occur, the pile foundation is marked as a settlement risk pile foundation, and the time point when the stress change is greater than the preset stress change value is marked and calibrated as a fixed time point for pile foundation anti-settlement; At the fixed time point of the pile foundation anti-settlement, longitudinal auxiliary piles are added to the settlement risk pile foundation, and the settlement severity is determined according to the predicted result of the stress change of the settlement risk pile foundation in a future preset time period, and the number of longitudinal auxiliary piles to be added is determined according to the settlement severity to obtain a second fixing scheme for the pile foundation, and the first fixing scheme and the second fixing scheme are integrated to obtain a pile foundation design and construction scheme.

7. A system for automatic optimization of pile position in deep soft soil, characterized in that: The system for automatic optimization of pile positions in deep soft soil comprises a storage device and a processor, wherein the storage device comprises a method program for automatic optimization of pile positions in deep soft soil, and when the method program for automatic optimization of pile positions in deep soft soil is executed by the processor, the following steps are implemented: Obtaining pile foundation design drawing data of the target project, and determining an initial design scheme for pile positions of the target project according to the design drawing data; Acquire geological parameters of the target engineering construction location, and perform adaptability evaluation on the initial design scheme of the pile position according to the geological parameters to obtain adaptability evaluation results; If the adaptability of the initial pile position design scheme is less than the adaptability threshold, the initial pile position design scheme is optimized based on a genetic algorithm to obtain an optimized pile position design scheme; Perform pile foundation construction according to the pile position design optimization plan, monitor the pile foundation surface stress change data in real time, predict the stress change in a future preset time period according to the pile foundation surface stress change data, and obtain the stress change prediction result; Evaluate the uniformity of the stress distribution on the pile foundation surface at each time point in a future preset time period according to the stress change prediction result, and obtain an evaluation result of the uniformity of the stress distribution on the pile foundation surface; Determining the pile foundation design and construction plan based on the pile foundation surface stress distribution uniformity assessment result; The uniformity of the stress distribution on the pile foundation surface at each time point in the future preset time period is evaluated according to the stress change prediction result, and the uniformity evaluation result of the stress distribution on the pile foundation surface is obtained, which is specifically: Visualizing the pile foundation surface stress at each time point within a preset time period according to the stress change prediction result to obtain a schematic diagram of the pile foundation surface stress at each time point; Converting the pile foundation surface stress schematic diagram at each time point into a thermal diagram to obtain a pile foundation surface stress thermal diagram at each time point; Calculating a color histogram of the pile foundation surface stress thermodynamic map, and obtaining a color value of each square grid according to the color histogram; Performing a clustering operation on the color values ​​based on a clustering algorithm to obtain a clustering result, and determining a clustering ratio and a color distribution area of ​​each color of the pile foundation surface stress thermodynamic map according to the clustering result; The pile foundation surface stress distribution is determined according to the clustering ratio and the color distribution area, and the uniformity of the pile foundation surface stress at each time point is evaluated according to the pile foundation surface stress distribution to obtain a pile foundation surface stress distribution uniformity evaluation result.

Images