Power transmission engineering pipe pile uplift bearing capacity intelligent prediction method and system

Abstract

The application relates to the technical field of geotechnical engineering, and particularly discloses a power transmission engineering pipe pile uplift bearing capacity intelligent prediction method and system, the method comprises the following steps: determining the limit uplift bearing capacity of each pipe pile in a preset sample area; acquiring the real-time load and pile head displacement of each pipe pile in an operation stage, and fitting a load response quantity; determining a coefficient distribution map according to the limit uplift bearing capacity of each pipe pile and the load response quantity thereof; receiving a user-inputted to-be-installed area, matching the coefficient distribution map in a dynamic database, and predicting the limit uplift bearing capacity based on the coefficient distribution map and pipe pile installation information; on the basis of predicting the limit uplift bearing capacity, actual use conditions are acquired through a sensor in an actual application stage, a dynamic influence coefficient determined by an area is generated, and the prediction results of subsequent same-type areas are corrected, so that the prediction accuracy is improved at a very low cost.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering technology, specifically to an intelligent prediction method and system for the pull-out bearing capacity of power transmission engineering pipe piles. Background Technology

[0002] In power transmission projects, pipe piles serve as the main load-bearing components of high-voltage transmission line tower foundations. Their tensile strength directly affects the structural safety and operational stability of the tower foundation under wind loads, icing loads, and long-term cyclic loading. Since transmission lines typically cross complex geological areas, pile foundations are significantly affected by soil conditions, groundwater variations, and environmental loads. Therefore, accurate assessment of tensile strength is of great engineering significance.

[0003] In practical engineering, the pull-out performance of pipe piles is affected by the coupling effect of multiple factors, resulting in obvious nonlinear and regional differences in pull-out bearing capacity. Traditional single-factor or simplified assumption methods are difficult to fully reflect the true stress state and have very low accuracy. In order to improve accuracy, some pure theoretical analysis methods based on finite element analysis have emerged in the existing technology. This method has greatly improved the prediction accuracy, and the computational resources consumed are acceptable to the construction party. However, it cannot be combined with the actual environment, and its accuracy is difficult to reach a very high level. In other words, the accuracy obtained based on a large amount of computational resources is difficult to meet the prediction accuracy. This solution has a very low cost-effectiveness. Therefore, how to further improve the prediction accuracy in a low-cost way on the finite element analysis prediction framework is the technical problem that this invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent prediction method and system for the pull-out bearing capacity of pipeline piles in power transmission projects, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for intelligent prediction of the pull-out bearing capacity of pipe piles in power transmission projects, the method comprising: The installation information of each pipe pile is obtained within a preset sample area, and the ultimate tensile bearing capacity of each pipe pile is determined based on the installation information. The installation information is used to characterize the condition of the pipe pile itself and the environmental condition. The real-time load and pile head displacement of each pipe pile during the operation phase are obtained, a sample set of real-time load to pile head displacement is constructed, and the load response quantity is fitted based on the sample set; the load response quantity is used to characterize the pipe pile's response to the load. The coefficient distribution map is determined based on the ultimate pull-out bearing capacity and load response of each pipe pile; the coefficient distribution map is used to characterize the dynamic influence at each location in the area. Obtain regional information of the sample area, compile statistical data on the regional information and its coefficient distribution map, and obtain a dynamic database; The system receives the installation area input by the user, matches the coefficient distribution map in the dynamic database, and predicts the ultimate tensile bearing capacity based on the coefficient distribution map and the pipe pile installation information.

[0006] As a further aspect of the present invention: the step of determining the coefficient distribution map based on the ultimate pull-out bearing capacity and load response of each pipe pile includes: Obtain a region map of the sample area; A grid is inserted into the regional map based on a preset step size, and a matrix template is generated based on the grid; the step size is used to adjust the side length of the grid cells. In a grid-containing area map, determine the mapping position corresponding to each pipe pile, and query the grid node closest to the mapping position as the grid node corresponding to the pipe pile; The first matrix is ​​obtained by statistically analyzing the ultimate tensile bearing capacity based on the matrix template, and the second matrix is ​​obtained by statistically analyzing the load response based on the matrix template. The row and column positions in the matrix correspond one-to-one with the grid nodes, and the elements use the data of the pipe piles corresponding to the grid nodes. When there are no pipe piles at the corresponding positions, the default empty data is used. The first and second matrices are both normalized to obtain the first normalized matrix and the second normalized matrix; the normalization process adopts the extreme value normalization process. Using the second normalized matrix as the numerator and the first normalized matrix as the denominator, the ratio matrix is ​​calculated. The coefficients of each element in the ratio matrix are transformed according to the mean to obtain the coefficient matrix. The coefficient matrix is ​​extended to determine the coefficient distribution map; the extension process is as follows: for empty data, query the nearest known data and replace the empty data.

[0007] As a further aspect of the present invention: the steps of obtaining regional information of the sample area, statistically analyzing the regional information and its coefficient distribution map to obtain a dynamic database include: Obtain the regional information of the sample area; the regional information is used to characterize the geographic information of the area, specifically a tag set; Statistical regional information and its coefficient distribution map are used to construct a database, with regional information as information items and coefficient distribution map as map items; Update commands are generated periodically to update various data items in the database.

[0008] As a further aspect of the present invention: the step of receiving the user-inputted installation area, matching a coefficient distribution map in a dynamic database, and predicting the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information includes: Receive the region to be installed from the user input and obtain the region information of the region to be installed; Based on the regional information, the information items in the dynamic database are traversed and matched to obtain a coefficient distribution map; Query the installation information of each pipe pile in the area to be installed, and determine the ultimate pull-out bearing capacity of each pipe pile based on the installation information. The coefficients corresponding to each pipe pile are queried in the coefficient distribution map, and the predicted ultimate tensile bearing capacity is corrected based on the coefficients.

[0009] As a further aspect of the present invention: the process of determining the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information includes: Geometric coefficients are calculated based on the pile's penetration depth, pile diameter, and length-to-diameter ratio. Soil coefficients are calculated based on average standard penetration test blow count, soil internal friction angle, and groundwater level depth. Based on geometric coefficients and soil quality coefficients, the composite bearing capacity coefficient is calculated and obtained. The environmental factor is calculated based on the number of load cycles and soil saturation. Correction coefficients are calculated based on pile roughness and environmental factors; Based on the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient, the predicted pull-out bearing capacity of the pipe pile is calculated.

[0010] As a further aspect of the present invention: the process for calculating and obtaining the predicted pull-out bearing capacity of the pipe pile is as follows: Obtain the reference bearing capacity, bearing capacity composite coefficient, and correction coefficient; Based on the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient, the predicted pull-out bearing capacity of the pipe pile is obtained through combined calculation. The predicted pull-out bearing capacity of the pipe pile is proportional to the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient.

[0011] The present invention also provides an intelligent prediction system for the pull-out bearing capacity of pipe piles in power transmission projects, the system comprising: The sample bearing capacity analysis module is used to acquire the pipe pile installation information of each pipe pile within a preset sample area, and to determine the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information; the pipe pile installation information is used to characterize the pipe pile's own state and the environmental state. The sample response analysis module is used to obtain the real-time load and pile head displacement of each pipe pile during the operation phase, construct a sample set of real-time load to pile head displacement, and fit the load response quantity based on the sample set; the load response quantity is used to characterize the pipe pile's response to the load. The coefficient identification output module is used to determine the coefficient distribution map based on the ultimate tensile bearing capacity and load response of each pipe pile; the coefficient distribution map is used to characterize the dynamic influence of each location in the area. The data statistics module is used to obtain regional information of the sample area, statistically analyze the regional information and its coefficient distribution map, and obtain a dynamic database; The bearing capacity matching module receives the installation area input by the user, matches the coefficient distribution map in the dynamic database, and predicts the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information.

[0012] As a further aspect of the present invention: the coefficient identification output module includes: The map acquisition unit is used to acquire a regional map of the sample area. A template generation unit is used to insert a grid into a region map based on a preset step size, and generate a matrix template based on the grid; the step size is used to adjust the side length of the grid cell. The node query unit is used to determine the mapping position corresponding to each pipe pile in a grid-containing area map, and query the grid node closest to the mapping position as the grid node corresponding to the pipe pile. The data statistics unit is used to calculate the ultimate tensile bearing capacity based on the matrix template to obtain the first matrix, and to calculate the load response based on the matrix template to obtain the second matrix. The rows and columns in the matrix correspond one-to-one with the grid nodes, and the elements use the data of the pipe piles corresponding to the grid nodes. When there are no pipe piles at the corresponding positions, the default empty data is used. The data normalization unit is used to normalize both the first matrix and the second matrix to obtain the first normalized matrix and the second normalized matrix; wherein, the normalization process adopts the extreme value normalization process. The coefficient matrix generation unit is used to calculate the ratio matrix by taking the second normalized matrix as the numerator and the first normalized matrix as the denominator. In the ratio matrix, the coefficients of each element are transformed according to the mean to obtain the coefficient matrix. The coefficient matrix extension unit is used to extend the coefficient matrix and determine the coefficient distribution map. The extension process is as follows: for empty data, query the nearest known data and replace the empty data.

[0013] As a further aspect of the present invention: the data statistics module includes: The regional information acquisition unit is used to acquire regional information of the sample area; the regional information is used to characterize the geographic information of the area, specifically a tag set. The database construction unit is used to statistically analyze regional information and its coefficient distribution map, using regional information as information items and coefficient distribution map as map items to construct the database. The timed update unit is used to generate update instructions on a regular basis to update various data items in the database.

[0014] As a further aspect of the present invention: the load-bearing capacity matching module includes: The data receiving unit is used to receive the area to be installed input by the user and obtain the area information of the area to be installed. The traversal matching unit is used to traverse the information items in the dynamic database based on regional information and match them to obtain a coefficient distribution map. The prediction execution unit is used to query the installation information of each pipe pile in the area to be installed, and determine the ultimate pull-out bearing capacity of each pipe pile based on the installation information. The coefficient application unit is used to query the coefficients corresponding to each pipe pile in the coefficient distribution map and correct the predicted ultimate tensile bearing capacity based on the coefficients.

[0015] Compared with the prior art, the beneficial effects of the present invention are: Based on the prediction of ultimate tensile bearing capacity, this invention, in the practical application stage, uses sensors to acquire actual usage data and generates dynamic influence coefficients determined by the region. These coefficients are then used to correct the prediction results for subsequent regions of the same type. The cost is extremely low, but the introduction of coefficients determined by the actual situation during the prediction process can at least serve as auxiliary information to indirectly improve the prediction accuracy. In addition, a comprehensive prediction scheme based on non-finite element analysis is introduced, which also achieves a high level of prediction accuracy while significantly reducing costs. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention.

[0017] Figure 1 The overall flowchart of the intelligent prediction method for the pull-out bearing capacity of pipe piles in power transmission projects is shown.

[0018] Figure 2 The structural diagram of the intelligent prediction system for the pull-out bearing capacity of pipe piles in power transmission projects is shown. Detailed Implementation

[0019] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0020] Figure 1 This is a flowchart illustrating the overall process of an intelligent prediction method for the pull-out bearing capacity of pipe piles in power transmission projects. In this embodiment of the invention, an intelligent prediction method for the pull-out bearing capacity of pipe piles in power transmission projects includes: Step S100: Obtain the pipe pile installation information of each pipe pile within a preset sample area, and determine the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information; the pipe pile installation information is used to characterize the pipe pile's own state and environmental state. The sample area refers to the area where pipe piles have been installed. After installation, the installation information of each pipe pile is obtained. The installation information is used to characterize the condition of the pipe pile itself and the environmental condition. By analyzing the installation information, the ultimate pull-out bearing capacity of each pipe pile can be predicted.

[0021] Step S200: Obtain the real-time load and pile head displacement of each pipe pile during the operation phase, construct a sample set of real-time load to pile head displacement, and fit the load response quantity based on the sample set; the load response quantity is used to characterize the pipe pile's response to the load. Sensors are installed simultaneously with the installation of the pipe piles to acquire real-time loads and pile head displacements during operation. These data reflect the actual working state of the pile head under load. It's important to note that in practice, displacement doesn't begin only after the ultimate tensile strength is reached; displacement occurs whenever a load is applied. For example, with an ultimate tensile strength of 800 kN, the displacement increases as follows: 0.3 mm at 100 kN; 1.2 mm at 300 kN; 4 mm at 500 kN; 20 mm at 750 kN; and rapidly increases at 800 kN. Displacement begins at 100 kN, but is far from the ultimate strength. The real-time loads and pile head displacements at the same moment (with a sufficiently small time difference) are used as a sample. All samples within a preset time range (generally, the current moment is used as the end point, and a preset time span is pushed forward) are statistically analyzed. This method obtains multiple real-time loads and their corresponding pile head displacements. Using the pile head displacement as the dependent variable and the real-time load as the independent variable, a parameter representing the pile's response to the load can be determined, called the load response quantity. The simplest way is to calculate the ratio of the pile head displacement to the real-time load and then calculate the mean. Alternatively, a function can be fitted, and the integral mean over a specific interval can be calculated. Furthermore, this load response quantity actually has units, which remain somewhat constant during calculation. Therefore, the real-time load and pile head displacement can be dimensionless first, and then only the numerical values ​​need to be calculated. The dimensionless processing can be done using an extremum method: select the maximum and minimum values, calculate the difference between the maximum and minimum values ​​as the first difference, and for any data point, calculate the difference between it and the minimum value as the second difference. Calculate the ratio of the second difference to the first difference to obtain data within the range of zero to one, which is used as the load response quantity.

[0022] Step S300: Determine the coefficient distribution map based on the ultimate pull-out bearing capacity and load response of each pipe pile; the coefficient distribution map is used to characterize the dynamic influence at each location in the area; The load response is obtained through actual measurement and calculation, while the ultimate tensile bearing capacity is obtained through theoretical calculation. Using the load response as actual data and the ultimate tensile bearing capacity as theoretical data, after normalization, the data becomes dimensionless and uniformly sized, ranging from zero to one (a similar normalization method has been mentioned in step S200). At this point, the ratio of the normalized load response to the ultimate tensile bearing capacity is calculated, yielding the ratio of the actual to the theoretical value. The mean of this ratio is calculated, representing the average situation within the sample area. This mean is then set to 1, determining the proportion of each location relative to the mean, representing the actual changes during operation. The calculated proportion is the coefficient. Furthermore, only the coefficient at the location of each pipe pile can be calculated. For the entire sample area, further extension is needed to obtain the coefficients at each location within the entire sample area (the differences within the same area are almost negligible). The accuracy of the extension process is naturally high, and the coefficient distribution map is obtained by statistical analysis in map form.

[0023] Step S400: Obtain the regional information of the sample area, statistically analyze the regional information and its coefficient distribution map, and obtain the dynamic database; The number of sample areas may not be unique. For each area after construction, the regional information of the sample area is obtained, and the regional information and its coefficient distribution map are statistically analyzed to obtain a database. The coefficient distribution map in the database represents the comprehensive deviation of this type of area in the actual work process, taking into account all factors. The regional information of each area generally does not change much, and the ultimate tensile bearing capacity is a theoretical value and will not change much either. However, the load response will change. Therefore, an adjustment port is added to the database, and the resulting database is a dynamic database.

[0024] Step S500: Receive the installation area input by the user, match the coefficient distribution map in the dynamic database, and predict the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information; Step S500 is the practical application stage. It receives the installation area input by the user, which is an area that has not yet been constructed. It queries the area information of the installation area, matches the coefficient distribution map in the dynamic database, and obtains the actual comprehensive changes of the pipe piles over time during the operation stage after construction. It predicts the information of the pipe piles, and makes overall corrections based on the coefficients to predict a more accurate ultimate pull-out bearing capacity.

[0025] Regarding step S300, the step of determining the coefficient distribution map based on the ultimate pull-out bearing capacity and load response of each pipe pile includes: Obtain a region map of the sample area; A grid is inserted into the regional map based on a preset step size, and a matrix template is generated based on the grid; the step size is used to adjust the side length of the grid cells. In a grid-containing area map, determine the mapping position corresponding to each pipe pile, and query the grid node closest to the mapping position as the grid node corresponding to the pipe pile. The first matrix is ​​obtained by statistically analyzing the ultimate tensile bearing capacity based on the matrix template, and the second matrix is ​​obtained by statistically analyzing the load response based on the matrix template. The row and column positions in the matrix correspond one-to-one with the grid nodes, and the elements use the data of the pipe piles corresponding to the grid nodes. When there are no pipe piles at the corresponding positions, the default empty data is used. The first and second matrices are both normalized to obtain the first normalized matrix and the second normalized matrix; the normalization process adopts the extreme value normalization process. Using the second normalized matrix as the numerator and the first normalized matrix as the denominator, the ratio matrix is ​​calculated. The coefficients of each element in the ratio matrix are transformed according to the mean to obtain the coefficient matrix. The coefficient matrix is ​​extended to determine the coefficient distribution map; the extension process is as follows: for empty data, query the nearest known data and replace the empty data.

[0026] The above describes the process of determining the coefficient distribution map. Obtaining the regional map of the sample area is a simple process of reading known data. A grid is inserted into the regional map based on a preset step size, which is used to adjust the side length of the grid cells. This is a basic function of the map tool. A matrix template is generated based on the grid. The mapping position corresponding to each pipe pile is determined in the grid-containing regional map. The grid node closest to the mapping position is queried and used as the grid node corresponding to the pipe pile. At this time, each pipe pile also corresponds to a row and column position in the matrix template. The ultimate tensile bearing capacity is statistically calculated based on the matrix template to obtain the first matrix. The load response is statistically calculated based on the matrix template to obtain the second matrix. If data is available, it is read directly; otherwise, the data at that row and column position is set as the default data. Both the first and second matrices are normalized to obtain the first and second normalized matrices. The normalization process uses an extremum normalization process, the specific process of which can be found in step S200.

[0027] Furthermore, using the second regularized matrix as the numerator and the first regularized matrix as the denominator, a ratio matrix is ​​calculated. While the description of this process is somewhat imprecise, its meaning is clear: it involves calculating the data at each row and column position in the matrix, dividing the data in the second regularized matrix by the values ​​in the first regularized matrix to obtain the ratio. The matrix composed of these ratios is called the ratio matrix. In the ratio matrix, coefficients are transformed based on the mean to obtain the coefficient matrix. The coefficient transformation is very simple: using the mean as the denominator, each element is calculated as a ratio to itself, and the resulting proportion is the coefficient. After calculating the coefficients corresponding to each pipe pile, the coefficients are inserted into the corresponding row and column positions. For rows and columns without corresponding pipe piles (i.e., empty data), the nearest known data is queried and used to replace the empty data. This extends the coefficient matrix, resulting in a coefficient distribution map.

[0028] Regarding step S400, the steps of obtaining regional information of the sample area, statistically analyzing the regional information and its coefficient distribution map, and obtaining the dynamic database include: Obtain the regional information of the sample area; the regional information is used to characterize the geographic information of the area, specifically a tag set; Statistical regional information and its coefficient distribution map are used to construct a database, with regional information as information items and coefficient distribution map as map items; Update commands are generated periodically to update various data items in the database.

[0029] Given a known coefficient distribution map, the process of obtaining the database is very simple. First, regional information of the sample area is acquired, including soil type, climate type, and area. This falls under the category of block evaluation schemes, and in this invention, it is assumed to be known data that can be directly read. This regional information is used to characterize the geographic information of the region, specifically a tag set. Then, the regional information and its coefficient distribution map are statistically analyzed, with the regional information as information items and the coefficient distribution map as map items, to construct the database. Based on this, update instructions are generated periodically to update each data item in the database, thus constructing a dynamic database.

[0030] Regarding step S500, the step of receiving the user-input area to be installed, matching the coefficient distribution map in the dynamic database, and predicting the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information includes: Receive the region to be installed from the user input and obtain the region information of the region to be installed; Based on the regional information, the information items in the dynamic database are traversed and matched to obtain a coefficient distribution map; Query the installation information of each pipe pile in the area to be installed, and determine the ultimate pull-out bearing capacity of each pipe pile based on the installation information. The coefficients corresponding to each pipe pile are queried in the coefficient distribution map, and the predicted ultimate tensile bearing capacity is corrected based on the coefficients.

[0031] The above refers to the application phase, which involves receiving the user-inputted area to be installed, obtaining the area information of the area to be installed, traversing the information items in the dynamic database based on the area information, matching to obtain a coefficient distribution map, querying the pipe pile installation information of each pipe pile in the area to be installed, determining the ultimate tensile bearing capacity of each pipe pile based on the pipe pile installation information, querying the coefficient corresponding to each pipe pile in the coefficient distribution map, and correcting the predicted ultimate tensile bearing capacity based on the coefficient.

[0032] As a preferred embodiment of the technical solution of the present invention, regarding the prediction process of the ultimate pull-out bearing capacity of the pipe piles mentioned above, there are some conventional prediction schemes in the prior art, but they are all relatively simple and singular. If computing power allows, a unique comprehensive prediction scheme is proposed in the example of the technical solution of the present invention. The process of determining the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information includes: Based on the pile's penetration depth, pile diameter, and length-to-diameter ratio, geometric coefficients are calculated and obtained. These geometric coefficients are used to quantify the influence of the pile's geometric characteristics on its pull-out bearing capacity, and they comprehensively consider factors such as the pile's penetration depth, pile diameter, and length-to-diameter ratio. Soil quality coefficients are calculated based on average SPT blow count, internal friction angle of soil, and groundwater depth. Soil quality coefficients are used to evaluate the contribution of soil conditions to uplift bearing capacity, and are mainly based on geotechnical parameters such as average SPT blow count, internal friction angle of soil, and groundwater depth. Based on geometric coefficients and soil coefficients, the composite bearing capacity coefficient is calculated and obtained. The composite bearing capacity coefficient is used to comprehensively reflect the combined effect of pile geometry and soil conditions on the pull-out bearing capacity of the pipe pile. The environmental coefficient is calculated based on the number of load cycles and soil saturation. The environmental coefficient is used to characterize the degree of attenuation or influence of external environmental factors, such as the number of load cycles and soil saturation, on the pull-out bearing capacity of the pipe pile. Based on the pile roughness and environmental factor, a correction factor is calculated and obtained; the correction factor is used to adjust the pull-out bearing capacity of the pipe pile, and it takes into account the combined effects of pile roughness and environmental factors. Based on the benchmark bearing capacity, bearing capacity composition coefficient, and correction coefficient, the predicted pull-out bearing capacity of the pipe pile is calculated. The benchmark bearing capacity refers to the initial value of the pull-out bearing capacity of the pipe pile obtained under standard or ideal conditions through traditional methods or empirical formulas, which can be initially calculated using the pull-out bearing capacity formula in the "Code for Design of Building Pile Foundations" (JGJ 94-2008). The predicted pull-out bearing capacity of the pipe pile refers to the predicted result of the pull-out bearing capacity of the pipe pile obtained by comprehensively considering various factors such as geometry, soil quality, environment, and interface through this method.

[0033] The intelligent prediction method for the pull-out bearing capacity of transmission engineering pipe piles proposed in this invention overcomes the limitations of traditional methods in analyzing the coupled effects of multiple factors by systematically considering the geometric characteristics of the pile, soil conditions, environmental factors, and pile-soil interface characteristics. This method provides a more comprehensive and physically meaningful prediction result, thereby improving the accuracy and reliability of predicting the pull-out bearing capacity of transmission engineering pipe piles and providing stronger technical support for tower foundation design and safety assessment.

[0034] Furthermore, the process for calculating and obtaining the predicted pull-out bearing capacity of the pipe pile is as follows: Obtain the baseline bearing capacity, bearing capacity composition coefficient, and correction coefficient. The baseline bearing capacity refers to the pull-out force that a pipe pile can withstand under ideal or standard conditions, and it serves as the basis for subsequent corrections and predictions. This baseline value can be obtained in various ways, such as based on engineering experience, theoretical calculation models (e.g., limit equilibrium method, elastic theory method, etc.), or through statistical analysis of small-scale test data on similar geological conditions and pile types. For example, an initial theoretical pull-out bearing capacity can be set based on the pile's material strength, cross-sectional dimensions, and a preliminary estimate of the pile-soil interface bond strength. Based on the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient, the predicted pull-out bearing capacity of the pipe pile is obtained through combined calculations. The predicted pull-out bearing capacity of the pipe pile is proportional to the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient. The specific calculation method is as follows: the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient are imported into the formula. Obtain the predicted pull-out bearing capacity of the pipe pile ,in, As the benchmark bearing capacity, The bearing capacity composite coefficient, This is a correction factor. The formula clarifies the multiplicative relationship between the parameters. This multiplicative model means that each coefficient affects the reference bearing capacity. The effects are interrelated and cumulative. For example, if the bearing capacity composite coefficient... A value of 0.8 indicates that pile geometry and soil conditions reduce the bearing capacity by 20%; if the correction factor... A value of 0.9 indicates that pile roughness and environmental factors further reduce the bearing capacity by 10%. Therefore, the final predicted pull-out bearing capacity of the pipe pile... It will be the benchmark bearing capacity This is 0.72 times, or a reduction of 28%. This calculation method is intuitive and easy to understand, and it can integrate complex engineering influencing factors through quantitative coefficients to obtain a comprehensive prediction result.

[0035] Through the above technical solution, this invention clarifies the specific calculation formula for predicting the pull-out bearing capacity of pipe piles, namely... This formula provides a clear and standardized mathematical model for integrating the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient. This effectively solves the problem of how to accurately and consistently combine these coefficients to arrive at the final prediction result after only calculating the individual coefficients. This multiplicative combination method ensures that the adjustment effects of various influencing factors (including pile geometry, soil conditions, pile-soil interface characteristics, and environmental factors) on the benchmark bearing capacity are reasonably and quantitatively reflected, thereby significantly improving the accuracy, reliability, and repeatability of predicting the pull-out bearing capacity of pipe piles, and providing more solid data support for the design and construction of pipe piles in power transmission projects.

[0036] In some of the above implementation methods, a method for calculating and obtaining the predicted pull-out bearing capacity of pipe piles based on the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient is proposed. However, in the process of obtaining the bearing capacity synthesis coefficient, how to effectively integrate the geometric conditions of the pile and the soil conditions, and quantify them in a way that can accurately reflect their influence on the pull-out bearing capacity of the pipe pile, is a problem that needs to be solved. Simply linearly combining geometric factors and soil factors may not be able to fully capture their complex interactions, thus affecting the accuracy of bearing capacity prediction. Therefore, specific processing procedures for the above parameters are required, as explained below: As a preferred embodiment of the technical solution of the present invention, the process for determining the geometric coefficients is defined, and the process for calculating and obtaining the geometric coefficients is as follows: Obtain the pile's embedment depth, diameter, and length-to-diameter ratio. Embedment depth refers to the actual depth to which the pile is embedded in the soil; its magnitude directly affects the utilization of pile side friction and is a crucial component of its uplift bearing capacity. Pile diameter is the cross-sectional dimension of the pile, relating to the pile side area and end area, and significantly influencing bearing capacity. The length-to-diameter ratio is the ratio of embedment depth to pile diameter, reflecting the pile's slenderness and significantly impacting its overall stress characteristics and stability. These parameters are fundamental data for assessing the contribution of pile geometry to uplift bearing capacity.

[0037] The depth of penetration, pile diameter, and length-to-diameter ratio are all subjected to maximum-min normalization to obtain the depth-to-penetration index, pile diameter index, and length-to-diameter ratio index. Maximum-min normalization is a commonly used data preprocessing technique. Its core purpose is to transform raw data with different dimensions or numerical ranges into a unified interval (e.g., between 0 and 1). Since the numerical ranges of physical quantities such as depth of penetration, pile diameter, and length-to-diameter ratio can vary significantly, directly using them for model calculations may lead to over-amplification or under-amplification of the influence of certain features. Normalization effectively eliminates the influence of dimensions, making different features comparable and ensuring that these geometric parameters contribute fairly to subsequent calculations, forming dimensionless indices that facilitate model learning and weight allocation.

[0038] The geometric coefficients are determined based on the penetration depth index, pile diameter index, and length-to-diameter ratio index. These geometric coefficients are scalar values ​​between 0 and 1, used to comprehensively characterize the favorable nature of the pile's geometric dimensions to its pull-out bearing capacity. The geometric coefficients increase with the favorable nature of any one of the penetration depth index, pile diameter index, or length-to-diameter ratio index. Specifically, the calculation method involves importing the penetration depth index, pile diameter index, and length-to-diameter ratio index into a formula. Obtaining geometric coefficients , A geometric coefficient close to 1 indicates a large embedment depth, reasonable pile diameter, and suitable length-to-diameter ratio, with geometric conditions extremely favorable for uplift bearing capacity. , , and All are weight coefficients with an output range of 0-1, and , The depth index is the pile diameter index. , This is the aspect ratio exponent. This formula is the core of calculating geometric coefficients, where... It is a sigmoid activation function that maps any real number to the interval (0,1), ensuring that the resulting geometric coefficients... It always lies between 0 and 1, giving its results a probabilistic or normalized interpretability. In the formula... , and These are the normalized penetration depth index, pile diameter index, and length-to-diameter ratio index. , and These are the corresponding weighting coefficients, which reflect the relative importance of each geometric parameter in influencing the pull-out bearing capacity. Their sum is 1, ensuring a reasonable allocation of weights. These weights can be assigned through a preset strategy or a dynamic algorithm. Using this weighted linear combination model based on the Sigmoid activation function, this method comprehensively considers the influence of pile penetration depth, pile diameter, and length-to-diameter ratio on the bearing capacity, and outputs a quantified geometric coefficient. .when A value close to 1 indicates that the pile's geometry (such as large embedment depth, reasonable pile diameter, and suitable length-to-diameter ratio) is extremely favorable to its pull-out bearing capacity, while the opposite is not true. This calculation method provides a structured and quantifiable approach to assess the contribution of pile geometry to bearing capacity.

[0039] Through the above technical solution, this invention provides a method for accurately quantifying the influence of pile geometry on pull-out bearing capacity. By performing maximum-minimum normalization on the embedment depth, pile diameter, and length-to-diameter ratio, the influence of different physical dimensions is eliminated, allowing these key geometric parameters to participate in the calculation on a unified scale. Furthermore, by employing a sigmoid function combined with a weighted linear combination, these normalized exponents are synthesized into a geometric coefficient between 0 and 1. This calculation model not only comprehensively considers the combined effects of the pile's geometric characteristics, but also uses weighting coefficients... , and The setting of these parameters allows for flexible adjustment of their importance, thus more accurately reflecting the contribution of geometric conditions to the tensile bearing capacity in actual engineering projects. Geometric coefficients The precise calculations significantly improved the composite coefficient of bearing capacity. The accuracy of the prediction, and thus the final predicted pull-out bearing capacity of the pipe pile. It is more reliable and provides a more scientific basis for the design and construction of pipe piles in power transmission projects, effectively avoiding the deviation in bearing capacity prediction caused by inaccurate evaluation of geometric parameters.

[0040] As a preferred embodiment of the technical solution of the present invention, the process for calculating and obtaining the soil coefficient is as follows: Obtain the average standard penetration test blow count, soil internal friction angle, and groundwater level depth; The average SPT blow count, soil internal friction angle and groundwater depth are respectively compared with their maximum values ​​to obtain the average SPT blow count index, soil internal friction angle index and groundwater depth index. The soil coefficient is obtained by continuously multiplying the average SPT blow count index, the soil internal friction angle index, and the groundwater level depth index, and then using a min function to limit the product to an upper limit of 1. , A soil quality coefficient close to 1 indicates that the soil conditions are excellent and the soil's contribution is fully utilized.

[0041] Obtain the average standard penetration test blow count, soil internal friction angle, and groundwater level depth; The average SPT blow count, internal friction angle, and groundwater depth are each compared to their maximum values ​​to obtain the average SPT blow count index, internal friction angle index, and groundwater depth index, respectively. This process transforms the original soil parameters into dimensionless standardized indices. This standardization is crucial to ensuring that different physical quantities contribute fairly and reasonably to the soil coefficients in subsequent calculations. By comparing each parameter to its respective maximum value, the problems of dimensional differences and inconsistent numerical ranges can be effectively eliminated, ensuring that all indices fall within a unified range, thus facilitating comprehensive evaluation. For example, the maximum value of the average SPT blow count can be determined based on local geological conditions, engineering experience, or relevant specifications. Dividing the actual measured average SPT blow count by this maximum value yields the average SPT blow count index. Similarly, for the internal friction angle of soil, its maximum value usually corresponds to dense sand or gravelly soil. Dividing the actual measured internal friction angle of soil by this maximum value yields the internal friction angle index. For the groundwater level depth, its maximum value can be set as the pile bottom depth or the local historical lowest water level depth. Dividing the actual measured groundwater level depth by this maximum value yields the groundwater level depth index. These maximum values ​​should be determined based on sufficient engineering geological survey data and regional experience to ensure the representativeness and accuracy of the index.

[0042] The soil coefficient is obtained by continuously multiplying the average SPT blow count index, the soil internal friction angle index, and the groundwater level depth index, and then using a min function to limit the product to an upper limit of 1. , A soil quality coefficient close to 1 indicates excellent soil conditions (high SPT blow count, large internal friction angle, and deep groundwater level), fully utilizing the soil's contribution. This multiplicative combination method reflects the "weakest link effect," meaning that any deficiency in any soil parameter (lower exponent value) will significantly reduce the final soil quality coefficient, thus more accurately reflecting the soil's comprehensive contribution to the pull-out bearing capacity of the pipe pile. Subsequently, a min function is used to limit the upper limit of the product to 1, ensuring the soil quality coefficient... The range of values ​​is within Within this range. This treatment method not only ensures the physical meaning of the soil quality coefficient, but also makes the soil quality coefficient... The closer to 1, the better the soil conditions, that is, the higher the standard penetration test blow number, the larger the internal friction angle, and the deeper the groundwater level, the more fully the soil can contribute to the pull-out bearing capacity of the pipe pile.

[0043] The above technical solution standardizes original soil parameters such as average SPT blow count, internal friction angle, and groundwater depth, effectively eliminating dimensional and numerical range differences between these parameters and ensuring they participate in the evaluation with uniform and reasonable weights in subsequent calculations. Based on this, by continuously multiplying these standardized indices and using a min function to limit the upper limit, the overall quality of the soil can be accurately and comprehensively reflected. This multiplicative combination mechanism makes the soil quality coefficient... It can sensitively capture the weaknesses of any soil parameter, thus avoiding the distortion of the overall soil quality assessment due to the poor performance of a single parameter. Ultimately, the obtained soil coefficients... It can more accurately and objectively quantify the contribution of soil to the pull-out bearing capacity of pipe piles, providing a more reliable input for the subsequent calculation of the bearing capacity synthesis coefficient, thereby significantly improving the accuracy and reliability of the prediction of the pull-out bearing capacity of pipe piles in power transmission projects.

[0044] As a preferred embodiment of the technical solution of the present invention, the process for calculating and obtaining the composite coefficient of bearing capacity is as follows: Obtain geometric coefficients and soil coefficients; Based on the geometric coefficient and the soil coefficient, the bearing capacity composite coefficient is calculated through a preset composite function, wherein the composite function makes the bearing capacity composite coefficient increase as the geometric coefficient and the soil coefficient increase, and the output value is between 0 and 1.

[0045] Geometric and soil coefficients are obtained; these coefficients have been pre-calculated or acquired. Geometric coefficients reflect the influence of the pile's physical dimensions and shape on bearing capacity, such as embedment depth, pile diameter, and length-to-diameter ratio. Soil coefficients characterize the contribution of the surrounding soil's engineering properties to bearing capacity, such as soil density, strength, and groundwater level. These two coefficients are key indicators for independently assessing pile and soil conditions, providing fundamental data for subsequent comprehensive evaluation.

[0046] Based on geometric coefficients and soil coefficients, a bearing capacity composite coefficient is calculated using a preset composite function. This composite function increases the bearing capacity composite coefficient as both the geometric coefficients and soil coefficients increase, and its output value is between 0 and 1. The specific calculation method for the composite function is as follows: The geometric coefficients and soil coefficients are imported into a formula... Obtain the composite coefficient of bearing capacity , A bearing capacity coefficient close to 1 indicates excellent geometric and soil conditions, with a large potential for foundation bearing capacity. Geometric coefficients This represents the soil quality coefficient. This formula uses a geometric mean, rather than a simple arithmetic mean. Its advantage lies in its ability to more sensitively reflect the limiting effect of any weak link in either the geometric or soil conditions on the overall bearing capacity. For example, even with excellent geometric conditions, poor soil conditions will significantly reduce the geometric mean, thus making the bearing capacity more limited. This more accurately reflects the actual bearing capacity potential. Bearing capacity composite coefficient. The range of values ​​is limited to Between, among which, when A value close to 1 indicates that both the pile's geometry and the soil conditions are excellent, suggesting that the foundation has significant uplift bearing capacity potential. This calculation method ensures... It can serve as an effective comprehensive evaluation indicator, providing an accurate correction factor for subsequent prediction of the pull-out bearing capacity of pipe piles.

[0047] Through the above technical solution, this invention effectively solves the problem of how to comprehensively quantify the influence of pile geometry and soil conditions on the pull-out bearing capacity of pipe piles. A geometric mean formula is used. To synthesize the bearing capacity composite coefficient Compared to simple linear combinations, this method can more accurately capture the nonlinear interaction between geometric and soil factors. Specifically, the geometric mean method suffers from a "weakest link" effect, meaning that when the geometric coefficients... or soil coefficient When any of the values ​​is low, the combined bearing capacity coefficient This will be significantly limited, thus avoiding the overestimation of the overall bearing capacity due to the superiority of a single aspect. This makes... This allows for a more realistic and conservative reflection of the actual bearing capacity potential of the pipe pile, improving the accuracy and reliability of the final prediction of the pipe pile's pull-out bearing capacity. Simultaneously, it will... The range of values ​​is limited to The physical meaning of the coefficient when it approaches 1 is clarified, which further enhances the intuitiveness and guidance of the coefficient in engineering applications and provides a more solid foundation for intelligent prediction of the pull-out bearing capacity of pipe piles in power transmission projects.

[0048] As a preferred embodiment of the technical solution of the present invention, the process for calculating and obtaining the environmental coefficient is as follows: Obtain the number of load cycles and soil saturation. The number of load cycles refers to the number of repeated loads that a pipe pile may experience during its service life. It has a significant impact on the long-term performance of the pile-soil interface and the stability of the soil structure, and is a crucial factor leading to the decrease in pull-out bearing capacity. This data can be obtained through engineering design specifications, historical monitoring data, field tests, or numerical simulations. Soil saturation refers to the water content in the soil pores. It directly affects the soil's strength, stiffness, permeability, and other mechanical properties. High saturation may lead to soil softening and pore water pressure accumulation, thereby reducing the shear strength of the pile-soil interface and the pull-out bearing capacity of the pile. Soil saturation can be obtained through field surveys, laboratory soil sample testing, or hydrogeological data analysis.

[0049] The load cycle count and soil saturation are compared with reference values ​​for load cycle count and soil saturation, respectively, to obtain the load cycle count index and soil saturation index. This ratioing process aims to standardize and dimensionless the original physical quantities, which have different dimensions and numerical ranges, transforming them into index values ​​between 0 and 1, thus facilitating subsequent mathematical model calculations and comparisons. The reference values ​​for load cycle count and soil saturation are typically determined based on engineering experience, industry standards, extensive experimental data, or the geological and hydrological conditions of a specific region, serving as benchmarks for measuring the relative influence of actual load cycle count and soil saturation. Through this ratioing process, the load cycle count index and soil saturation index can intuitively reflect the severity of actual environmental conditions compared to ideal or benchmark conditions.

[0050] The load cycle influence index and saturation influence index are input into the attenuation function to calculate the environmental coefficient. The environmental coefficient decreases monotonically with the increase of the load cycle influence index and the saturation influence index, and the environmental coefficient is greater than 0 and not greater than 1. The attenuation function is calculated by importing the load cycle number index and the soil saturation index into the formula. Obtain environmental coefficient , An environmental coefficient close to 1 indicates no cyclic loading, dry soil, and no environmental degradation. Environmental degradation coefficient, The load cycle number index. This represents the soil saturation index. The formula employs an exponential decay model, effectively quantifying the combined impact of cyclic loading and soil saturation on the environmental decay of the pull-out bearing capacity of pipe piles. Among these factors, The environmental degradation coefficient is a parameter reflecting the sensitivity of bearing capacity to environmental factors. Its value can be determined through fitting a large amount of experimental data, numerical simulation, or engineering experience. Environmental coefficient The range of values ​​is When the environmental coefficient When the value is close to 1, it indicates that the environmental conditions of the pipe pile are close to ideal, i.e., there is no cyclic load and the soil is dry. At this time, the attenuation effect of the environment on the bearing capacity is minimal or negligible. Conversely, when... The smaller the value, the more significant the attenuation effect of environmental factors on carrying capacity.

[0051] Through the above technical solution, this invention can accurately quantify the comprehensive attenuation effect of load cycle number and soil saturation on the pull-out bearing capacity of pipe piles. By introducing an exponential attenuation model, the standardized load cycle number index and soil saturation index are organically combined, thus improving the environmental coefficient. It can more accurately reflect the degree of bearing capacity reduction under actual environmental conditions.

[0052] As a preferred embodiment of the technical solution of the present invention, the process for calculating and obtaining the correction coefficient is as follows: Obtaining pile roughness and environmental coefficients is crucial. Pile roughness refers to the frictional characteristics of the interface between the pipe pile surface and the surrounding soil. Its magnitude directly affects the shear strength of the pile-soil interface, and consequently, the pull-out bearing capacity of the pipe pile. The environmental coefficient reflects the attenuation effect of external environmental factors (such as the number of load cycles and soil saturation) on the pull-out bearing capacity of the pipe pile. Obtaining these parameters is the basis for subsequent calculations of correction factors. Pile roughness can be obtained through field measurements, laboratory tests, or empirical values ​​based on pile material type and construction technology. The environmental coefficient is calculated based on external environmental conditions, such as load cycle characteristics and soil moisture content.

[0053] The pile roughness index is obtained by comparing the pile roughness value with the maximum roughness value in the training dataset. Obtaining the pile roughness index aims to standardize the original pile roughness values, placing them within a uniform dimensional range to facilitate subsequent comprehensive calculations with other coefficients. By comparing the index with the maximum roughness value in the training dataset, roughness data of different magnitudes can be mapped to a range between 0 and 1, thereby eliminating the influence of dimensions and ensuring the stability and accuracy of the correction coefficient calculation.

[0054] The average value of the sum of pile roughness and environmental factor is taken as the correction factor. , A correction factor close to 1 indicates high pile roughness, low environmental degradation, superior interface conditions, and environmental friendliness. (Correction factor) This method is used to comprehensively quantify the impact of pile interface conditions and environmental factors on the pull-out bearing capacity of pipe piles. By summing and averaging the standardized pile roughness index and the environmental coefficient, an index that comprehensively reflects the pile-soil interface quality and environmental friendliness can be obtained. This averaging method ensures a balanced weighting of the two factors in the correction coefficient. Correction coefficient The range of values ​​is A value close to 1 indicates high pile roughness and low environmental attenuation, meaning superior pile-soil interface conditions and minimal impact of the external environment on bearing capacity, thus making the actual pull-out bearing capacity of the pipe pile closer to its theoretical benchmark value.

[0055] Through the above technical solution, this application can accurately quantify the contribution of pile roughness to the pull-out bearing capacity of pipe piles and comprehensively evaluate the attenuation effect of the environmental factor on the bearing capacity. By standardizing the pile roughness and averaging it with the environmental factor, the correction coefficient can comprehensively reflect the combined influence of pile-soil interface conditions and the external environment. The introduction of this correction coefficient allows the prediction model to more accurately capture the subtle influences of pile characteristics and environmental changes on the bearing capacity in actual engineering projects, thereby significantly improving the accuracy and reliability of pipe pile pull-out bearing capacity prediction and providing a more precise basis for the design and construction of pipe piles in power transmission projects.

[0056] Figure 2 A structural diagram of an intelligent prediction system for the pull-out bearing capacity of pipe piles in power transmission projects is shown. In a preferred embodiment of the technical solution of the present invention, an intelligent prediction system for the pull-out bearing capacity of pipe piles in power transmission projects is also provided. The system 10 includes: The sample bearing capacity analysis module 11 is used to acquire the pipe pile installation information of each pipe pile in a preset sample area, and determine the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information; the pipe pile installation information is used to characterize the pipe pile's own state and environmental state. The sample response analysis module 12 is used to acquire the real-time load and pile head displacement of each pipe pile during the operation phase, construct a sample set of real-time load to pile head displacement, and fit the load response quantity based on the sample set; the load response quantity is used to characterize the pipe pile's response to the load. The coefficient identification output module 13 is used to determine the coefficient distribution map based on the ultimate pull-out bearing capacity and load response of each pipe pile; the coefficient distribution map is used to characterize the dynamic influence of each location in the area. Data statistics module 14 is used to obtain regional information of the sample area, statistically analyze the regional information and its coefficient distribution map, and obtain a dynamic database; The bearing capacity matching module 15 is used to receive the installation area input by the user, match the coefficient distribution map in the dynamic database, and predict the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information.

[0057] Furthermore, the coefficient recognition output module 13 includes: The map acquisition unit is used to acquire a regional map of the sample area. A template generation unit is used to insert a grid into a region map based on a preset step size, and generate a matrix template based on the grid; the step size is used to adjust the side length of the grid cell. The node query unit is used to determine the mapping position corresponding to each pipe pile in a grid-containing area map, and query the grid node closest to the mapping position as the grid node corresponding to the pipe pile. The data statistics unit is used to calculate the ultimate tensile bearing capacity based on the matrix template to obtain the first matrix, and to calculate the load response based on the matrix template to obtain the second matrix. The rows and columns in the matrix correspond one-to-one with the grid nodes, and the elements use the data of the pipe piles corresponding to the grid nodes. When there are no pipe piles at the corresponding positions, the default empty data is used. The data normalization unit is used to normalize both the first matrix and the second matrix to obtain the first normalized matrix and the second normalized matrix; wherein, the normalization process adopts the extreme value normalization process. The coefficient matrix generation unit is used to calculate the ratio matrix by taking the second normalized matrix as the numerator and the first normalized matrix as the denominator. In the ratio matrix, the coefficients of each element are transformed according to the mean to obtain the coefficient matrix. The coefficient matrix extension unit is used to extend the coefficient matrix and determine the coefficient distribution map. The extension process is as follows: for empty data, query the nearest known data and replace the empty data.

[0058] Specifically, the data statistics module 14 includes: The regional information acquisition unit is used to acquire regional information of the sample area; the regional information is used to characterize the geographic information of the area, specifically a tag set. The database construction unit is used to statistically analyze regional information and its coefficient distribution map, using regional information as information items and coefficient distribution map as map items to construct the database. The timed update unit is used to generate update instructions on a regular basis to update various data items in the database.

[0059] Furthermore, the load-bearing capacity matching module 15 includes: The data receiving unit is used to receive the area to be installed input by the user and obtain the area information of the area to be installed. The traversal matching unit is used to traverse the information items in the dynamic database based on regional information and match them to obtain a coefficient distribution map. The prediction execution unit is used to query the installation information of each pipe pile in the area to be installed, and determine the ultimate pull-out bearing capacity of each pipe pile based on the installation information. The coefficient application unit is used to query the coefficients corresponding to each pipe pile in the coefficient distribution map and correct the predicted ultimate tensile bearing capacity based on the coefficients.

[0060] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for intelligent prediction of the pull-out bearing capacity of pipe piles in power transmission projects, characterized in that, The method includes: The installation information of each pipe pile is obtained within a preset sample area, and the ultimate tensile bearing capacity of each pipe pile is determined based on the installation information. The installation information is used to characterize the condition of the pipe pile itself and the environmental condition. The real-time load and pile head displacement of each pipe pile during the operation phase are obtained, a sample set of real-time load to pile head displacement is constructed, and the load response quantity is fitted based on the sample set; the load response quantity is used to characterize the pipe pile's response to the load. The coefficient distribution map is determined based on the ultimate pull-out bearing capacity and load response of each pipe pile; the coefficient distribution map is used to characterize the dynamic influence at each location in the area. Obtain regional information of the sample area, compile statistical data on the regional information and its coefficient distribution map, and obtain a dynamic database; The system receives the installation area input by the user, matches the coefficient distribution map in the dynamic database, and predicts the ultimate tensile bearing capacity based on the coefficient distribution map and the pipe pile installation information. The steps for determining the coefficient distribution map based on the ultimate pull-out bearing capacity and load response of each pipe pile include: Obtain a region map of the sample area; A grid is inserted into the regional map based on a preset step size, and a matrix template is generated based on the grid; the step size is used to adjust the side length of the grid cells. In a grid-containing area map, determine the mapping position corresponding to each pipe pile, and query the grid node closest to the mapping position as the grid node corresponding to the pipe pile; The first matrix is ​​obtained by statistically analyzing the ultimate tensile bearing capacity based on the matrix template, and the second matrix is ​​obtained by statistically analyzing the load response based on the matrix template. The row and column positions in the matrix correspond one-to-one with the grid nodes, and the elements use the data of the pipe piles corresponding to the grid nodes. When there are no pipe piles at the corresponding positions, the default empty data is used. The first and second matrices are both normalized to obtain the first normalized matrix and the second normalized matrix; the normalization process adopts the extreme value normalization process. Using the second normalized matrix as the numerator and the first normalized matrix as the denominator, the ratio matrix is ​​calculated. The coefficients of each element in the ratio matrix are transformed according to the mean to obtain the coefficient matrix. The coefficient matrix is ​​extended to determine the coefficient distribution map; the extension process is as follows: for empty data, query the nearest known data and replace the empty data.

2. The intelligent prediction method for the pull-out bearing capacity of pipeline piles in power transmission projects according to claim 1, characterized in that, The steps of obtaining regional information of the sample area, statistically analyzing the regional information and its coefficient distribution map to obtain a dynamic database include: Obtain the regional information of the sample area; the regional information is used to characterize the geographic information of the area, specifically a tag set; Statistical regional information and its coefficient distribution map are used to construct a database, with regional information as information items and coefficient distribution map as map items; Update commands are generated periodically to update various data items in the database.

3. The intelligent prediction method for the pull-out bearing capacity of pipeline piles in power transmission projects according to claim 1, characterized in that, The steps of receiving the installation area input by the user, matching the coefficient distribution map in the dynamic database, and predicting the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information include: Receive the region to be installed from the user input and obtain the region information of the region to be installed; Based on the regional information, the information items in the dynamic database are traversed and matched to obtain a coefficient distribution map; Query the installation information of each pipe pile in the area to be installed, and determine the ultimate pull-out bearing capacity of each pipe pile based on the installation information. The coefficients corresponding to each pipe pile are queried in the coefficient distribution map, and the predicted ultimate tensile bearing capacity is corrected based on the coefficients.

4. The intelligent prediction method for the pull-out bearing capacity of transmission engineering pipe piles according to any one of claims 1 to 3, characterized in that, The process of determining the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information includes: Geometric coefficients are calculated based on the pile's penetration depth, pile diameter, and length-to-diameter ratio. Soil coefficients are calculated based on average standard penetration test blow count, soil internal friction angle, and groundwater level depth. Based on geometric coefficients and soil quality coefficients, the composite bearing capacity coefficient is calculated and obtained. The environmental factor is calculated based on the number of load cycles and soil saturation. Correction coefficients are calculated based on pile roughness and environmental factors; Based on the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient, the predicted pull-out bearing capacity of the pipe pile is calculated.

5. The intelligent prediction method for the pull-out bearing capacity of pipeline piles in power transmission projects according to claim 4, characterized in that, The process for calculating and obtaining the predicted pull-out bearing capacity of the pipe pile is as follows: Obtain the reference bearing capacity, bearing capacity composite coefficient, and correction coefficient; Based on the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient, the predicted pull-out bearing capacity of the pipe pile is obtained through combined calculation. The predicted pull-out bearing capacity of the pipe pile is proportional to the benchmark bearing capacity, the bearing capacity synthesis coefficient, and the correction coefficient.

6. An intelligent prediction system for the pull-out bearing capacity of pipe piles in power transmission projects, characterized in that, The system includes: The sample bearing capacity analysis module is used to acquire the pipe pile installation information of each pipe pile within a preset sample area, and to determine the ultimate pull-out bearing capacity of each pipe pile based on the pipe pile installation information; the pipe pile installation information is used to characterize the pipe pile's own state and the environmental state. The sample response analysis module is used to acquire the real-time load and pile head displacement of each pipe pile during the operation phase, construct a sample set of real-time load to pile head displacement, and fit the load response quantity based on the sample set; the load response quantity is used to characterize the pipe pile's response to the load. The coefficient identification output module is used to determine the coefficient distribution map based on the ultimate tensile bearing capacity and load response of each pipe pile; the coefficient distribution map is used to characterize the dynamic influence of each location in the area. The data statistics module is used to obtain regional information of the sample area, statistically analyze the regional information and its coefficient distribution map, and obtain a dynamic database; The bearing capacity matching module is used to receive the installation area input by the user, match the coefficient distribution map in the dynamic database, and predict the ultimate pull-out bearing capacity based on the coefficient distribution map and the pipe pile installation information. The coefficient identification output module includes: The map acquisition unit is used to acquire a regional map of the sample area. A template generation unit is used to insert a grid into a region map based on a preset step size, and generate a matrix template based on the grid; the step size is used to adjust the side length of the grid cell. The node query unit is used to determine the mapping position corresponding to each pipe pile in a grid-containing area map, and query the grid node closest to the mapping position as the grid node corresponding to the pipe pile. The data statistics unit is used to calculate the ultimate tensile bearing capacity based on the matrix template to obtain the first matrix, and to calculate the load response based on the matrix template to obtain the second matrix. The rows and columns in the matrix correspond one-to-one with the grid nodes, and the elements use the data of the pipe piles corresponding to the grid nodes. When there are no pipe piles at the corresponding positions, the default empty data is used. The data normalization unit is used to normalize both the first matrix and the second matrix to obtain the first normalized matrix and the second normalized matrix; wherein, the normalization process adopts the extreme value normalization process. The coefficient matrix generation unit is used to calculate the ratio matrix by taking the second normalized matrix as the numerator and the first normalized matrix as the denominator. In the ratio matrix, the coefficients of each element are transformed according to the mean to obtain the coefficient matrix. The coefficient matrix extension unit is used to extend the coefficient matrix and determine the coefficient distribution map. The extension process is as follows: for empty data, query the nearest known data and replace the empty data.

7. The intelligent prediction system for the pull-out bearing capacity of power transmission engineering pipe piles according to claim 6, characterized in that, The data statistics module includes: The regional information acquisition unit is used to acquire regional information of the sample area; the regional information is used to characterize the geographic information of the area, specifically a tag set. The database construction unit is used to statistically analyze regional information and its coefficient distribution map, using regional information as information items and coefficient distribution map as map items to construct the database. The timed update unit is used to generate update instructions on a regular basis to update various data items in the database.

8. The intelligent prediction system for the pull-out bearing capacity of power transmission engineering pipe piles according to claim 6, characterized in that, The load-bearing capacity matching module includes: The data receiving unit is used to receive the area to be installed input by the user and obtain the area information of the area to be installed. The traversal matching unit is used to traverse the information items in the dynamic database based on regional information and match them to obtain a coefficient distribution map. The prediction execution unit is used to query the installation information of each pipe pile in the area to be installed, and determine the ultimate pull-out bearing capacity of each pipe pile based on the installation information. The coefficient application unit is used to query the coefficients corresponding to each pipe pile in the coefficient distribution map and correct the predicted ultimate tensile bearing capacity based on the coefficients.

Images