Method and system for predicting uplift bearing capacity of mud mixed pile

Abstract

The invention provides a method and system for predicting the uplift bearing capacity of a mud mixed pile. According to the method, modeling is carried out by integrating geomechanics and monitoring data. The method comprises the following steps: firstly, acquiring geometric parameters of a multi-layer heterogeneous soil layer interface, constructing a database through a mechanical test, and improving the reliability by combining gradient recognition and cooperative verification of pile deformation and load data; dividing longitudinal segmentation units, adjusting anti-slip parameters to generate a space mapping table, establishing a debonding dynamic model containing an interlayer retardation effect, simulating a debonding expansion process, and outputting load evolution data. And judging the maximum load of the critical state based on data convergence analysis, and taking the maximum load as a predicted value of the uplift bearing capacity. According to the technical scheme, through dynamic parameter mapping and debonding process simulation, accurate prediction of the uplift bearing capacity of the pile foundation in a complex soil layer is achieved, and the defect that a traditional model is insufficient in characterization of interlayer heterogeneity and dynamic debonding behaviors is overcome.

Description

Technical Field

[0001] The present application relates to the technical field of pile foundation bearing capacity analysis and prediction, and particularly relates to a method and system for predicting the uplift bearing capacity of slurry mixing piles. Background Art

[0002] The accurate prediction of the uplift bearing capacity of slurry mixing piles in complex soil layers with alternating sand and clay is a key problem in the anti-floating design of underground structures. In actual engineering, due to factors such as differences in soil layer components and uneven penetration of solidified slurry at the pile-soil interface, debonding and slip behaviors are likely to occur. Traditional static models are difficult to characterize the dynamic effects of interlayer heterogeneity on debonding expansion. There is an urgent need for a prediction method that integrates multi-source data and dynamically simulates the debonding process to improve reliability.

[0003] Currently, the mainstream solution adopts a layered homogenization model combined with the static equilibrium theory. By simplifying multi-layer soil layers into homogenized units and calculating the anti-slip force of each layer based on the average interface parameters obtained from laboratory tests, the overall uplift bearing capacity is predicted after superposition. This method introduces an interlayer shear force reduction coefficient to correct the influence of heterogeneity and uses the pile body strain monitoring data to invert the load distribution.

[0004] Although the existing layered homogenization model achieves calculation efficiency through the simplification of soil layer units and the static equilibrium theory, its homogenization assumption ignores the blocking effect of the soil layer transition zone and the spatial differences in debonding behavior, resulting in the accumulation of errors in interlayer shear force transmission. At the same time, the static equilibrium framework cannot characterize the non-linear dynamic process of debonding from local triggering to multi-level cascading expansion, is difficult to capture the critical state mutation characteristics, and has poor adaptability to new slurry ratios or complex soil layer combinations relying on empirically calibrated reduction coefficients. Eventually, the prediction results have a high degree of dispersion and insufficient reliability. Summary of the Invention

[0005] The present application provides a method and system for predicting the uplift bearing capacity of slurry mixing piles to solve the problem in the prior art that the dynamic effects of interlayer heterogeneity and the non-linear process of debonding expansion cannot be accurately characterized.

[0006] In a first aspect, the present application provides a method for predicting the uplift bearing capacity of slurry mixing piles, including:

[0007] Obtaining the geometric characteristic parameters of the interface structure formed by the solidified slurry in multi-layer heterogeneous soil layers under different ratios;

[0008] Determining the interface mechanical parameters of the multi-layer heterogeneous soil layers through mechanical tests, and constructing an interface mechanical database in combination with the geometric characteristic parameters;

[0009] Collecting pile body deformation monitoring data and load monitoring data, generating deformation gradient features by identifying the deformation mutation threshold, and performing collaborative verification on the load monitoring data and the deformation gradient features;

[0010] The pile body is divided into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layer, and the anti-slip parameters in the interface mechanics database are adjusted based on the soil layer component ratio in each segmented unit to generate a spatial anti-slip parameter mapping table;

[0011] An interface debonding dynamics model is established. By inputting the spatial anti-slip parameter mapping table and the verified deformation gradient characteristics, and combining the interlayer blocking effect parameters, the spatially differentiated expansion process of the debonding behavior is simulated, and the evolution data related to the load and depth is output;

[0012] Based on the convergence relationship between the evolution data and the deformation gradient characteristics, the maximum load threshold corresponding to the debonding critical expansion state is determined as the predicted value of the uplift bearing capacity.

[0013] Optionally, the collection of the pile body deformation monitoring data and the load monitoring data, the generation of the deformation gradient characteristics by identifying the deformation mutation threshold, and the collaborative verification of the load monitoring data and the deformation gradient characteristics include:

[0014] Collect the multi-dimensional deformation monitoring data on the surface of the pile body and the load monitoring data at the pile top synchronously at fixed time intervals;

[0015] Perform continuous spatial scanning on the deformation monitoring data, locate the adjacent areas with sudden changes in deformation values as the mutation areas, extract the deformation increase amplitude and the direction change angle in the mutation areas, and generate a set of deformation mutation thresholds;

[0016] According to the extreme points of the increase amplitude in the set of deformation mutation thresholds, divide the deformation gradient intervals longitudinally along the pile body, calculate the change rate of the deformation increase amplitude with depth in each deformation gradient interval, and generate the deformation gradient characteristics;

[0017] Match the load monitoring data with the generation time stamp of the deformation gradient characteristics according to the collection time stamp, and screen out the synchronous change intervals of the load increase amplitude and the deformation gradient increase amplitude;

[0018] Perform amplitude ratio verification on the load data and the deformation gradient characteristics in the synchronous change interval. If the ratio of the load increase amplitude to the deformation gradient increase amplitude exceeds the preset fluctuation range, the abnormal data segment is removed, and the verified deformation gradient characteristics are output.

[0019] Optionally, the division of the pile body into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layer, the adjustment of the anti-slip parameters in the interface mechanics database based on the soil layer component ratio in each segmented unit, and the generation of the spatial anti-slip parameter mapping table include:

[0020] Extract the longitudinal distribution profile of the soil layers around the pile according to the borehole exploration data, divide the pile body into multiple concentric ring-shaped segment units at preset depth intervals, calculate the volume ratios of sand and clay within each of the segment units, and convert the volume ratios into soil layer component proportion coefficients;

[0021] Extract the foundation anti-slip parameters corresponding to sand and clay from the interface mechanics database, and linearly superimpose the foundation anti-slip parameters corresponding to sand and clay respectively according to the soil layer component proportion coefficients to generate an anti-slip composite parameter adapted to the current segment unit;

[0022] Arrange the depth positions of the segment units and the corresponding anti-slip composite parameters in a longitudinal order to form a one-dimensional anti-slip parameter mapping table indexed by depth;

[0023] Based on the one-dimensional anti-slip parameter mapping table, non-linearly interpolate the anti-slip composite parameters of adjacent segment units according to the soil layer transition gradient to generate a continuous anti-slip parameter field;

[0024] Spatially bind the continuous anti-slip parameter field to the three-dimensional geometric model of the pile body, and output the global anti-slip parameter distribution map of the pile-soil interface as a spatial anti-slip parameter mapping table.

[0025] Optionally, to establish the interface debonding dynamics model, by inputting the spatial anti-slip parameter mapping table and the verified deformation gradient characteristics, and combining the interlayer blocking effect parameters to simulate the spatially differentiated expansion process of the debonding behavior, and output the evolution data of the load-depth correlation, including:

[0026] Based on the spatial anti-slip parameter mapping table, construct a pile-soil interface mechanics network with segment units as nodes;

[0027] Input the verified deformation gradient characteristics into the pile-soil interface mechanics network, calculate the difference between the deformation gradient and the anti-slip composite parameter at each node, and generate a debonding trigger criterion for the node;

[0028] According to the interlayer blocking effect parameters, define the resistance weight for the debonding expansion between adjacent nodes. If the current node meets the debonding trigger criterion, then calculate the expansion probability of debonding to adjacent nodes according to the resistance weight;

[0029] Using the load monitoring data as a time-series driving signal, iteratively update the debonding state of each node. When the debonding expands from the surface node to the deep node, record the load value at the time of debonding trigger for each depth node;

[0030] Aggregate the load values at the time of debonding trigger for all nodes and their corresponding depths to generate the evolution data of the load with the increase of the debonding depth.

[0031] Optionally, aggregating the load values and corresponding depths of all nodes when debonding is triggered to generate evolution data of the load as the debonding depth increases includes:

[0032] Traversing all nodes in the pile-soil interface mechanical network, sorting the nodes from shallow to deep according to their depth, and extracting the load value and depth position of each node when debonding is first triggered;

[0033] The depth intervals between adjacent nodes are checked for continuity. If the depth difference between adjacent nodes exceeds a preset threshold, a virtual node is inserted into the interval and the load value of the previous node is linearly distributed to the virtual node according to the depth difference.

[0034] Integrate the load values and depths of the actual nodes and the virtual nodes in a triggering order to generate an initial load depth sequence;

[0035] Detecting the presence of multiple load values at the same depth in the initial load depth sequence, retaining the maximum load value and removing redundant data points to form a final data point;

[0036] The final data points are arranged in order of increasing depth to generate continuous and monotonic load evolution data with increasing debonding depth.

[0037] Optionally, the determining, based on the convergence relationship between the evolution data and the deformation gradient characteristics, a maximum load threshold corresponding to the critical extension state of debonding as a prediction value of the pull-out bearing capacity includes:

[0038] Extracting the increase slope of the load changing with the debonding depth in the evolution data, and marking the depth point where the increase slope reverses direction for the first time as the first critical point;

[0039] Extracting the deformation increase corresponding to the depth of the first critical point from the deformation gradient feature, and marking it as the second critical point if the deformation increase exceeds a set multiple of the historical average increase;

[0040] The depth difference between the first critical point and the second critical point is recorded. When the depth difference is less than the preset tolerance, the load value corresponding to the two is determined to be the maximum load threshold of the critical extension state of debonding. When the depth difference exceeds the preset tolerance, the load application time is extended until a stable point where the load increase returns to zero appears in the evolution data. The last load peak before the stable point is taken as the maximum load threshold, and the maximum load threshold is output as the predicted value of the pull-out bearing capacity of the pile foundation.

[0041] Optionally, the determining the interface mechanical parameters of the multi-layer heterogeneous soil layer by mechanical test and constructing an interface mechanical database in combination with the geometric characteristic parameters comprises:

[0042] Prepare a composite soil sample with alternating layers of sandy soil and clay, and embed a solidified slurry in the composite soil sample to form a simulated pile-soil interface;

[0043] Apply multi-level tensile loads to the simulated pile-soil interface, monitor the load values and displacement amounts during the interface separation process, and extract the peak points of the load-displacement curve as the interface tensile strength;

[0044] After the interface is completely separated, measure the frictional sliding resistance of the separation surface, and calculate the interface friction angle according to the variation relationship between the sliding displacement and the frictional sliding resistance;

[0045] Extract the surface undulation height and the proportion of the contact area of the simulated pile-soil interface to generate a set of geometric characteristic parameters;

[0046] Match the interface tensile strength with the set of interface friction angles under each set of ratios, and establish interface mechanical parameters indexed by the ratio number;

[0047] Aggregate the set of geometric characteristic parameters and the interface mechanical parameters under all ratio numbers to generate an interface mechanical database containing the mapping relationship between ratio, geometry and mechanics.

[0048] In a second aspect, the present application provides a prediction system for the uplift bearing capacity of a slurry mixing pile, including:

[0049] An acquisition module that acquires geometric characteristic parameters of the interface structure formed by the solidified slurry in multi-layer heterogeneous soil layers under different ratios;

[0050] The acquisition module further includes determining the interface mechanical parameters of the multi-layer heterogeneous soil layer through mechanical tests, and constructing an interface mechanical database in combination with the geometric characteristic parameters;

[0051] A verification module that collects pile deformation monitoring data and load monitoring data, generates a deformation gradient feature by identifying the deformation mutation threshold, and performs collaborative verification on the load monitoring data and the deformation gradient feature;

[0052] A generation module that divides the pile into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layer, adjusts the anti-slip parameters in the interface mechanical database based on the soil layer component ratio within each segmented unit, and generates a spatial anti-slip parameter mapping table;

[0053] An evolution module that establishes an interface debonding dynamics model, inputs the spatial anti-slip parameter mapping table and the verified deformation gradient feature, and simulates the spatially differentiated expansion process of the debonding behavior in combination with the interlayer blocking effect parameters, and outputs the evolution data related to the load and depth;

[0054] The prediction module determines the maximum load threshold corresponding to the critical debonding expansion state as the predicted value of the uplift bearing capacity based on the convergence relationship between the evolution data and the deformation gradient feature.

[0055] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for predicting the uplift bearing capacity of a slurry mixing pile as described in the first aspect above.

[0056] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements a method for predicting the uplift bearing capacity of a slurry mixing pile as described in the first aspect.

[0057] In an embodiment of the present application, geometric feature parameters of the interface structure formed by the solidified slurry in a multi-layer heterogeneous soil layer under different ratios are obtained; the interface mechanical parameters of the multi-layer heterogeneous soil layer are measured through mechanical tests, and an interface mechanical database is constructed in combination with the geometric feature parameters; pile deformation monitoring data and load monitoring data are collected, a deformation gradient feature is generated by identifying the deformation mutation threshold, and the load monitoring data and the deformation gradient feature are co-verified; the pile body is divided into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layer, and the anti-slip parameters in the interface mechanical database are adjusted based on the soil component ratio in each segmented unit to generate a spatial anti-slip parameter mapping table; an interface debonding dynamics model is established, and by inputting the spatial anti-slip parameter mapping table and the verified deformation gradient feature, combined with the interlayer blocking effect parameter, the spatially differentiated expansion process of the debonding behavior is simulated, and the evolution data related to the load and depth is output; based on the convergence relationship between the evolution data and the deformation gradient feature, the maximum load threshold corresponding to the critical debonding expansion state is determined as the predicted value of the uplift bearing capacity.

[0058] The technical solution of the present application has the following beneficial effects:

[0059] In the present application, a multi-dimensional database is constructed by obtaining the geometric feature parameters and mechanical test data of the interface of a multi-layer heterogeneous soil layer, and the gradient features of the pile body deformation and load monitoring data are co-verified to achieve highly reliable fusion of dynamic monitoring data; longitudinal segmented units are divided based on the spatial distribution of the soil layer and the anti-slip parameters are dynamically adapted to generate a mapping table, breaking through the static limitations of the homogenization model; through the interface debonding dynamics model, the interlayer blocking effect and three-dimensional parameter mapping are integrated to accurately simulate the spatially differentiated expansion process of the debonding behavior, and combined with the convergence analysis of the evolution data and the deformation characteristics, the critical state mutation point is effectively captured, and finally the high-precision prediction of the uplift bearing capacity in complex soil layers is realized, significantly improving the comprehensive characterization ability of interlayer heterogeneity, dynamic debonding behavior and load evolution non-linearity.

[0060] Further, multi-dimensional deformation data of the pile body and pile top load data are synchronously collected at fixed time intervals. The deformation mutation area is located by continuous space scanning, and the increase amplitude and direction angle are extracted to generate a mutation threshold set. The deformation gradient interval is longitudinally divided based on the threshold extreme points, and the change rate of the deformation increase amplitude with depth in each interval is calculated to form a gradient feature. The load data is matched with the deformation gradient feature according to the time stamp, the synchronous change interval of the load deformation increase amplitude is screened, and the abnormal data segment is eliminated through amplitude ratio verification, and the verified gradient feature with high confidence is output. Through dynamic synchronous monitoring and multi-dimensional deformation mutation threshold recognition, abnormal data caused by equipment errors or external interference is effectively excluded, and the spatio-temporal evolution law of the load change and the deformation gradient is accurately correlated. Combining the amplitude ratio verification mechanism to strengthen data consistency significantly improves the authenticity and reliability of the deformation gradient feature, provides high-precision input for the subsequent debonding dynamics model, and enhances the anti-interference ability and critical state capture accuracy of the uplift bearing capacity prediction.

[0061] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0063] Figure 1 The flowchart of a method for predicting the uplift bearing capacity of a slurry mixing pile provided by the present application is shown;

[0064] Figure 2 The scenario diagram of a method for predicting the uplift bearing capacity of a slurry mixing pile provided by the present application is shown;

[0065] Figure 3 The structural schematic diagram of a system for predicting the uplift bearing capacity of a slurry mixing pile provided by the present application is shown;

[0066] Figure 4 The structural schematic diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0068] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any order of execution. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0069] Research has found that there are significant challenges in predicting the uplift bearing capacity of slurry mixing piles in complex soil layers with alternating sandy and clay layers. Traditional static models are difficult to accurately characterize the slip behavior of the pile-soil interface because they ignore the dynamic effects of interlayer heterogeneity and the nonlinear process of debonding expansion. Although existing layered homogenization models improve the calculation efficiency through soil layer homogenization simplification and static equilibrium superposition, their homogenization assumptions mask the blocking effect in the transition zone and the spatial differences in debonding, and the static framework cannot simulate the cascade expansion process of debonding. In addition, relying on empirical reduction coefficients results in poor adaptability to new types of slurries or complex soil layers, ultimately leading to a high dispersion and insufficient reliability of the prediction results.

[0070] To address the above problems, this application proposes a method for predicting the uplift bearing capacity of slurry mixing piles. The core lies in breaking through the limitations of traditional static models through collaborative modeling of geometric and mechanical parameters, verification of spatio-temporal monitoring data, and three-dimensional differential debonding simulation. First, obtain the geometric parameters of the interfaces of multi-layer heterogeneous soil layers and construct an interface mechanical database through mechanical tests; synchronously collect pile deformation and load data, and improve data reliability through the collaborative verification of deformation mutation thresholds and gradient characteristics; divide longitudinal segmented units based on the spatial distribution of soil layers, dynamically adjust anti-slip parameters to generate a three-dimensional mapping table; establish a debonding dynamics model with interlayer blocking effects to simulate the spatially differential expansion process of debonding behavior and output load-depth evolution data; finally, through the convergence analysis of the evolution data and deformation characteristics, accurately determine the maximum load threshold at the critical state. This method effectively characterizes the blocking effect of interlayer heterogeneity on interface slip through the multi-source fusion of geometric and mechanical parameter databases and dynamic monitoring data, and solves the problem of spatial error accumulation in the homogenization model; based on the three-dimensional differential simulation of the debonding dynamics model, it fully restores the nonlinear process of debonding from local triggering to multi-level cascade expansion, breaking through the bottleneck of capturing the mutation characteristics of the static equilibrium framework; at the same time, through the dynamic adaptation of soil layer segment parameters and the data-driven verification mechanism, it reduces the dependence on empirical reduction coefficients, significantly improves the adaptability to new slurry ratios and complex soil layer combinations, and realizes the accurate prediction of the uplift bearing capacity of pile foundations in complex soil layers.

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0072] Figure 1 The figure is a flowchart of a method for predicting the uplift bearing capacity of a slurry mixing pile provided by an embodiment of the present application. As Figure 1 shown, the method includes:

[0073] 101. Obtain the geometric characteristic parameters of the interface structure formed by the solidified slurry in multi-layer heterogeneous soil layers under different ratios;

[0074] In the above solution, the geometric characteristic parameters refer to the morphological quantification indexes of the interface structure between the solidified slurry and the soil layer in multi-layer heterogeneous soil layers, including the interface penetration width, interface roughness, branch network density, and interface inclination angle. These parameters are obtained through three-dimensional scanning and image analysis techniques and are used to characterize the spatial heterogeneity of the interface structure under different slurry ratios.

[0075] In the embodiment of the present application, first, three-dimensional imaging of the multi-layer heterogeneous soil solidified slurry complex sampled on-site is performed through CT scanning technology to obtain high-resolution images of the interface structure under different slurry ratios;

[0076] Secondly, a digital image edge detection algorithm is used to perform layered processing on the three-dimensional image, identify the contact boundary between the slurry and the soil layer, and extract the interface penetration width and branch network density;

[0077] Then, using three-dimensional surface reconstruction technology, a quantification model of the interface roughness is generated based on point cloud registration and surface fitting, and the distribution characteristics of the interface inclination angle are calculated through principal component analysis;

[0078] Finally, the penetration width, roughness, branch density, and inclination angle data under different ratios are integrated into a structured database to form a set of geometric characteristic parameters, providing spatial morphology input for subsequent mechanical parameter matching and anti-slip analysis.

[0079] In practical applications, first, a three-dimensional tomography of the soil composite sample of the slurry mixing pile drilled on-site is performed by a high-resolution industrial CT scanner, such as the X5000 series, to obtain the original image data of the penetration interface structure of the solidified slurry in the alternating layers of sand and clay under different slurry ratios, and the resolution is controlled within 10 μm to capture the microscopic morphology. Subsequently, a layered slice analysis of the three-dimensional scan data is performed using an image processing module based on the Canny edge detection algorithm. The contact boundary between the slurry and the soil layer is identified through multi-threshold adaptive gray-scale segmentation technology, and the lateral penetration width, branch network density, and geometric features of the interface contour are extracted. On this basis, the layered slice data is reconstructed into a three-dimensional space model using point cloud registration technology, the interface roughness is quantified by combining the non-uniform rational B-spline surface fitting method, and the statistical mean and variance of the angle between the slurry diffusion direction and the pile axis are calculated through principal component analysis to obtain the interface dip angle distribution. Finally, the penetration width, roughness, branch density, and dip angle data under different ratios are classified and stored according to the soil layer type to construct a structured geometric feature parameter database, providing spatially heterogeneous inputs for subsequent mechanical parameter matching and anti-slip analysis.

[0080] The overall solution of the above 101 systematically obtains the geometric feature parameters of the interface structure under different slurry ratios through high-precision three-dimensional imaging and quantitative analysis technology, overcoming the characterization blind spots of traditional manual measurement for microscopic morphologies such as penetration branches and roughness. Through the construction of a structured parameter set, spatially heterogeneous input data is provided for subsequent dynamic anti-slip analysis, supporting the accurate modeling of the interlayer blocking effect and the debonding propagation path, and fundamentally improving the reliability and adaptability of the prediction of the uplift bearing capacity in complex soil layers.

[0081] 102. Determine the interface mechanical parameters of the multi-layer heterogeneous soil layer through mechanical tests, and construct an interface mechanical database in combination with the geometric feature parameters;

[0082] Optionally, step 102 may specifically include the following steps:

[0083] 1021. Prepare a composite soil sample containing alternating layers of sand and clay, and embed a solidified slurry in the composite soil sample to form a simulated pile-soil interface;

[0084] 1022. Apply multi-level tensile loads to the simulated pile-soil interface, monitor the load values and displacement amounts during the interface separation process, and extract the peak points of the load-displacement curve as the interface tensile strength;

[0085] 1023. After the interface is completely separated, measure the frictional sliding resistance of the separation surface, and calculate the interface friction angle according to the variation relationship between the sliding displacement and the frictional sliding resistance;

[0086] 1024. Extract the surface undulation height and contact area ratio of the simulated pile-soil interface to generate a set of geometric feature parameters;

[0087] 1025. At each mix ratio, perform parameter matching on the interface tensile strength and the set of interface friction angles to establish interface mechanical parameters indexed by the mix ratio number;

[0088] 1026. Aggregate the set of geometric feature parameters and the interface mechanical parameters at all mix ratio numbers to generate an interface mechanical database containing the mapping relationship between mix ratio, geometry, and mechanics.

[0089] In the above solution, the simulated pile-soil interface refers to the pile-like contact surface formed by artificial preparation, including the reproduction of the real stratum structure with alternating sand and clay layers, including the cross-linking and penetration morphology of the solidified slurry and the soil, which can be used to restore the mechanical and geometric properties of the actual pile-soil interface. The interface tensile strength refers to the maximum bearing capacity when the pile-soil interface separates under the action of a tensile load, which can be used to characterize the ultimate performance of the interface against debonding failure. The interface friction angle refers to the angular parameter corresponding to the ratio of the sliding resistance to the normal stress during the sliding stage of the pile-soil interface, which can be used to quantify the residual friction characteristics after interface debonding. The set of geometric feature parameters refers to a set of quantitative indicators describing the surface morphology of the pile-soil interface, including the surface undulation height distribution data obtained by three-dimensional laser scanning, including the contact area ratio and the roughness fractal dimension, which can be used to reveal the spatial influence law of the geometric morphology on the interface mechanical behavior. The interface mechanical database refers to an associated data system integrating the interface mechanical and geometric parameters under different mix ratios, including the mechanical parameters and geometric parameters indexed by the mix ratio number, including a multi-dimensional relational data structure, which can provide high-fidelity input for the dynamic prediction of the uplift bearing capacity.

[0090] In the embodiments of the present application, first, based on the borehole data on the engineering site through step 1021, determine the thickness ratio of the sand and clay layers, and use a pneumatic layered compactor to fill the soil samples layer by layer. The thickness error after each layer is compacted is controlled within a certain range to ensure that the interlayer transition morphology is consistent with the actual stratum. Drill a vertical hole in the center of the soil sample, inject the solidified slurry with a preset mix ratio, and let it stand and cure for 72 hours to form a simulated pile body with a diameter scaled proportionally to the pile body prototype, ensuring that the slurry penetration range and the cross-linking morphology of the soil are close to the actual working conditions. Perform a CT scan on the cured pile-soil interface to confirm that there are no voids or crack defects, and verify through the shear wave velocity test that the deviation of the interlayer density of the soil sample from the field data is less than a certain preset value.

[0091] Next, fix the composite soil sample to the upper and lower clamps of the tensile testing machine through step 1022, set the loading rate to 0.1mm / s, cover the range to 1.2 times the estimated limit load, and turn on the force sensor and displacement meter simultaneously. Load step by step according to the 10kN gradient, maintain each load for 30 seconds to eliminate creep interference, and record the load displacement curve; use the filtering algorithm to smooth the noise, and identify the peak point of the curve through the local extreme value search algorithm. The load value corresponding to the peak point is taken as the interface tensile strength.

[0092] Then, in step 1023, a normal pressure is applied to the separated interface to simulate the self-weight stress of the soil layer, and the pressure is maintained constant by the servo hydraulic system. The interface is pulled along the sliding direction at a rate of 0.5 mm / s, and the curve of the change of sliding resistance with displacement is recorded; the moving average algorithm is used to smooth the data and extract the mean resistance value in the stable stage. The interface friction angle is calculated according to the Coulomb friction law, and the specific calculation formula is as follows: , where the normal pressure is , the sliding resistance is , the interface friction angle is .

[0093] Secondly, in step 1024, a line laser scanner is used to perform multi-angle scanning on the separated interface to generate three-dimensional point cloud data, and the multi-view data is registered by the ICP algorithm to reconstruct the complete interface morphology. The fractal dimension algorithm is used to calculate the surface undulation height distribution, extract the maximum peak-to-valley difference, average roughness and fractal dimension; the three-dimensional point cloud data is projected onto a two-dimensional plane, and the contact area and non-contact area are distinguished by the threshold segmentation algorithm, the actual contact pixel ratio is counted, and the spatial distribution uniformity index of the contact area is calculated; in order to generate a set of geometric feature parameters.

[0094] Again, through step 1025, the parameters such as interface tensile strength, interface friction angle, undulation height, contact area ratio under a single group ratio are encoded as key-value pairs in JSON format, with the ratio number as the unique identifier. For example, the ratio number of "S40-C60-P7-3" with sand ratio of 40%, clay ratio of 60%, and slurry ratio number P7-3 is {"tensile strength": 38,"friction angle": 14,"undulation height": 0.8} stored in JSON format. The parameter set is stored in a relational database, and a primary key and foreign key association table is established to support joint queries based on multiple conditions such as sand ratio and slurry type.

[0095] Finally, the parameter sets of all the mixes are deduplicated and checked in step 1026, outliers are removed, and an interface mechanics database is generated. A three-dimensional data cube is constructed in the interface mechanics database, and the dimensions include the mix number, soil layer ratio, and slurry type. The measurement values include mechanical parameters and geometric parameters, and the debonding dynamics model is opened to call through the API interface.

[0096] In practical applications, taking the alternating layers of 45% sand and 55% clay as an example, the interface mechanics database is constructed using the method of the present invention. First, according to the layer thickness ratio of the geological survey report, a pneumatic layered compactor is used to prepare a composite soil sample, and the sand layer and the clay layer are laid alternately, with a single layer thickness of 15cm sand and 18cm clay, and a total height of 1.2m; a 10cm diameter solidified slurry cement and bentonite ratio of 7:3 and a water-cement ratio of 0.6 is pre-buried in the center of the soil sample. The simulated pile-soil interface is formed after curing for 72 hours, and the shear wave velocity test verifies that the density deviation is less than the preset value. The soil sample is installed in a 200kN tensile testing machine, loaded in stages at a rate of 0.1mm / s, and the load-displacement curve is collected synchronously. After filtering and noise reduction, the peak load is identified as 53.7kN, and the tensile strength is calculated to be 53.7kN, and the critical strain energy. A normal pressure of 120 kPa was applied to the separation interface, and the sliding traction was carried out at a rate of 0.5 mm / s. The average sliding resistance was measured to be 34.2 kPa, and the interface friction angle was calculated to be 15.8. A line laser scanner was used to obtain the three-dimensional point cloud data of the interface. After ICP registration and denoising, the average surface undulation height was calculated to be 1.2 mm. The above parameters were bound to the mix number "S45-C55-P7-3" and stored in JSON format as {"tensile strength": 53.7,"friction angle": 15.8,"undulation height": 1.2}. This mix was aggregated with the other 12 groups of mix data to construct a three-dimensional relationship table, with fields including soil layer ratio, slurry type, mechanical parameters, and geometric parameters, and was opened to the debonding dynamics model through the API interface.

[0097] The overall solution of 102 mentioned above, through the preparation of composite soil samples and the fusion of multi-dimensional parameters, constructs a high-precision interface mechanics database, and systematically solves the problem of pull-out prediction of complex soil layers. First, the simulated pile-soil interface is prepared based on the alternating layers of sand and clay to reproduce the real stratum structure; the tensile strength of the interface is accurately extracted through multi-stage tensile tests, and the residual friction characteristics after debonding are quantified by combining dynamic monitoring of sliding resistance and calculation of friction angle; three-dimensional laser scanning and image analysis technology are used to obtain geometric features such as surface undulation height and contact area ratio, revealing the spatial influence of morphology on mechanical behavior. Further, with the ratio number as the index, the mechanical parameters and geometric features are dynamically matched to form a structured multi-dimensional database, breaking through the simplification limitations of the traditional homogenization model on interlayer heterogeneity and transition zone blocking effect. Finally, the mechanical geometry coupling data supports the spatial mapping of anti-slip parameters and the debonding dynamics simulation, significantly improving the adaptability of complex ratios and soil layer combinations, reducing the dependence on empirical coefficients, and providing a data base with both theoretical rigor and engineering practicality for the prediction of pull-out bearing capacity.

[0098] 103. Collecting pile deformation monitoring data and load monitoring data, generating deformation gradient features by identifying deformation mutation thresholds, and collaboratively verifying the load monitoring data and the deformation gradient features;

[0099] Optionally, step 103 may specifically include the following steps:

[0100] 1031. synchronously collecting multi-dimensional deformation monitoring data of the pile body surface and load monitoring data of the pile top at fixed time intervals;

[0101] 1032. Perform continuous spatial scanning on the deformation monitoring data, locate adjacent areas where deformation values suddenly change as sudden change areas, extract deformation increase and direction change angle of the sudden change areas, and generate a set of deformation sudden change threshold values;

[0102] 1033. According to the amplification extreme value points in the deformation mutation threshold set, the deformation gradient intervals are divided along the longitudinal direction of the pile body, and the change rate of the deformation amplification with depth in each deformation gradient interval is calculated to generate a deformation gradient feature;

[0103] 1034. Perform event synchronization matching on the load monitoring data according to the acquisition timestamp and the generation timestamp of the deformation gradient feature, and filter out the synchronous change interval of the load increase and the deformation gradient increase;

[0104] 1035. Perform amplitude ratio verification on the load data and the deformation gradient characteristics within the synchronous change interval. If the ratio of the load increase to the deformation gradient increase exceeds a preset fluctuation range, remove the abnormal data segment and output the verified deformation gradient characteristics.

[0105] In the above scheme, deformation monitoring data refers to the multi-dimensional displacement and strain signals collected by sensors on the surface of the pile body, including dynamic change information of axial tension, radial compression and bending deformation, which can be used to characterize the structural response of the pile body under pull-out load. Load monitoring data refers to the instantaneous pull-out load value recorded by the pile top sensor, including load size, action direction and time evolution trend, which is used to quantify the mechanical input of external load to the pile-soil system. The deformation mutation threshold set refers to the characteristic parameter set of the local mutation area of the pile body deformation extracted by spatial scanning, including the deformation amplitude mutation amount, mutation direction angle and spatial coordinate information, which is used to locate the starting point and expansion path of the debonding and slipping behavior. The deformation gradient feature refers to the distribution of the rate of change of deformation increase with depth in the deformation gradient interval divided along the longitudinal direction of the pile body, including gradient slope, spatial continuity and strength attenuation characteristics, which is used to describe the three-dimensional expansion strength and interlayer blocking effect of debonding behavior.

[0106] In the embodiment of the present application, first, data synchronization acquisition is realized through the distributed sensor network in step 1031. An optical fiber grating sensor array is uniformly arranged on the surface of the pile body, symmetrically distributed at a fixed axial spacing, and multi-dimensional deformation data such as axial strain, radial displacement, and bending curvature are collected at a fixed sampling frequency. At the same time, a high-precision hydraulic sensor is installed at the top of the pile to record the instantaneous value of the load at the same sampling frequency. The data synchronization is realized through the clock protocol to ensure that the timestamp alignment error of the deformation and load data is less than 1 ms.

[0107] Next, based on the dynamic mutation detection of the spatial sliding window, the sliding window algorithm is used to perform spatial continuous scanning on the pile body deformation data. Calculate the standard deviation of the deformation values within each window. If the change rate of the standard deviation between adjacent windows is greater than a certain threshold, it is marked as a mutation region. Further extract the deformation increase amplitude and the direction change angle of the mutation region. The deformation increase amplitude, direction change angle, and spatial coordinates of all mutation regions constitute the deformation mutation threshold set.

[0108] Then, according to the extreme points of the deformation increase amplitude in the mutation threshold set in step 1033, the deformation gradient intervals are divided along the longitudinal direction of the pile body. For example, each interval is 0.5 m. Within each interval, the least squares method is used to linearly fit the deformation increase amplitude and the depth, and the deformation gradient slope is calculated. The specific calculation formula is as follows: , where k is the deformation gradient slope, is the deformation increase amplitude, is the depth change, and then its confidence level is calculated. Finally, a deformation gradient characteristic curve including the depth range, gradient slope, and confidence level of each interval is generated.

[0109] Secondly, through step 1034, the time series of the load monitoring data is aligned with the generated timestamp of the deformation gradient characteristics, and the dynamic time warping algorithm is used to compensate for the sensor response delay, such as the mechanical hysteresis difference between the hydraulic sensor and the optical fiber sensor. After time alignment, the Pearson correlation coefficient of the load increase amplitude and the deformation gradient increase amplitude is calculated with a sliding window, and the time periods with a Pearson correlation coefficient greater than 0.8 are selected as the synchronous change intervals, and the low-correlation noise segments are removed.

[0110] Finally, in the synchronous change interval through step 1035, the ratio of the load increase amplitude to the deformation gradient increase amplitude is calculated frame by frame. The reasonable fluctuation range of the ratio is preset to be 0.8 to 1.2, and this ratio can be adjusted according to the slurry mix ratio. If the ratio exceeds this range in consecutive fixed-frame data, it is determined as an abnormal segment. The abnormal segment data is smoothed and repaired using a filter. If it still does not meet the threshold after repair, it is directly removed. Finally, the verified deformation gradient characteristic curve and the associated load data are output.

[0111] In practical applications, first, a micro strain gauge array is symmetrically arranged on the surface of a simulated pile with a diameter of 50 mm and a height of 400 mm in the laboratory at an axial spacing of 0.1 m and 2 groups circumferentially to collect axial strain and radial displacement data, and the sampling frequency is maintained at 10 Hz. A micro load sensor with a range of 50 kN is installed at the pile top to synchronously record the load data, and the deformation and load timestamps are synchronized through a hardware trigger signal. During the construction loading stage, when the load gradually increases to 8 kN, the mutation rate of the deformation standard deviation at a depth of 0.15 m in the pile body is detected to reach 65%. The deformation increase in this area is extracted as 0.15 mm, and the direction angle pointing to the clay layer side is 42°, and it is incorporated into the mutation threshold set. Based on the mutation extreme points, the gradient interval is divided. In the interval of 0.1 - 0.3 m, the least squares method is used to fit the relationship between the deformation increase and the depth, and the calculated gradient slope is 0.15 mm / m, indicating that the debonding behavior accelerates and expands upward from this area. After aligning the load data through the dynamic time warping algorithm, the Pearson correlation coefficient between the deformation gradient increase and the load increase is 0.85 during the period when the load increases from 6 kN to 9 kN, which is determined as the effective synchronization interval. During the verification, it is found that the ratio of the load increase to the deformation gradient increase continuously reaches 1.52 for 3 frames within a certain 0.2 s period, exceeding the preset threshold of 0.8 - 1.2. It is confirmed as the vibration interference of the loading device motor. After filtering and smoothing, it still exceeds the limit, so this abnormal section is removed. The finally output calibrated deformation gradient characteristic curve shows that when the load reaches 10.5 kN, the gradient slope in the interval of 0.3 - 0.4 m suddenly rises to 0.22 mm / m. Combining the convergence analysis of the evolution data, it is determined that the maximum load threshold corresponding to the debonding critical state is 11 kN, with a deviation of only 1.8% from the laboratory destructive test result of 11.2 kN, verifying the high precision and reliability of this scheme in predicting the uplift bearing capacity in complex soil layers.

[0112] The overall scheme of the above 103 significantly improves the data reliability by synchronously collecting the multi-dimensional deformation and load monitoring data of the pile body, combining the spatial mutation threshold identification and gradient feature extraction, and dynamically correlating the load change and the deformation evolution law. Based on the accurate positioning of the deformation mutation area and the gradient interval division, it effectively characterizes the spatial blocking effect of the interlayer heterogeneity on the debonding behavior; through the timestamp synchronization matching and amplitude ratio verification mechanism, abnormal interferences such as sensor drift and external shocks are removed to ensure the consistency of the dynamic response of the load deformation. The finally output high-confidence deformation gradient characteristics and evolution data provide accurate input for the debonding dynamics model, completely restoring the non-linear process of debonding from local triggering to multi-level cascading expansion, breaking through the limitations of traditional static models in capturing the mutation characteristics of the critical state, and realizing the high-precision prediction of the uplift bearing capacity in complex soil layers, with both engineering applicability and anti-interference ability.

[0113] 104. Divide the pile body into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layer, and adjust the anti-slip parameters in the interface mechanics database based on the soil layer component ratio in each segmented unit to generate a spatial anti-slip parameter mapping table;

[0114] Optionally, step 104 may specifically include the following steps:

[0115] 1041. Extract the longitudinal distribution profile of the soil layer around the pile according to the borehole exploration data, divide the pile body into multiple concentric annular segmented units at a preset depth interval, calculate the volume ratios of sand and clay inside each segmented unit, and convert the volume ratios into soil layer component ratio coefficients;

[0116] 1042. Extract the basic anti-slip parameters corresponding to sand and clay from the interface mechanics database, and linearly superimpose the basic anti-slip parameters corresponding to sand and clay respectively according to the soil layer component ratio coefficients to generate an anti-slip composite parameter adapted to the current segmented unit;

[0117] 1043. Arrange the depth positions of each segmented unit and the corresponding anti-slip composite parameters in a longitudinal order to form a one-dimensional anti-slip parameter mapping table indexed by depth;

[0118] 1044. Based on the one-dimensional anti-slip parameter mapping table, non-linearly interpolate the anti-slip composite parameters of adjacent segmented units according to the soil layer transition gradient to generate a continuous anti-slip parameter field;

[0119] 1045. Spatially bind the continuous anti-slip parameter field to the three-dimensional geometric model of the pile body, and output the global anti-slip parameter distribution map of the pile-soil interface as the spatial anti-slip parameter mapping table.

[0120] In the above solution, the soil layer component ratio coefficient refers to a weight parameter that quantifies the volume ratios of sand and clay in a heterogeneous soil layer, including the complementary relationship between the sand coefficient and the clay coefficient, and can be used to dynamically adjust the anti-slip parameters to adapt to the spatial heterogeneity of the soil layer. The anti-slip composite parameter refers to a comprehensive mechanical parameter that characterizes the equivalent anti-slip ability of a heterogeneous soil layer, including the linearly weighted superposition result of the basic anti-slip parameters of sand and clay, including the proportional fusion value of the friction angle and the cohesion, and can be used to describe the interface anti-slip strength of the mixed soil layer. The one-dimensional anti-slip parameter mapping table refers to a longitudinal anti-slip parameter set indexed by depth, which can be used to initially reflect the longitudinal variation law of the anti-slip ability of the pile-soil interface. The continuous anti-slip parameter field refers to a spatial distribution field that describes the gradual change characteristics of the anti-slip ability of the soil layer around the pile, and can be used to eliminate the segmented mutation error of the discrete model. The spatial anti-slip parameter mapping table refers to a three-dimensional dynamic description model of the global anti-slip ability of the pile-soil interface, including the binding relationship between the continuous anti-slip parameter field and the pile body geometric model, including the distribution heat map of the parameters in the three-dimensional space, and can be used to drive the high-precision simulation of the debonding dynamics model.

[0121] In the embodiment of the present application, first, through step 1041, the longitudinal distribution profile of the soil layer around the pile is extracted based on the borehole exploration data, and the alternating distribution law of sandy soil and clay layer is identified through geological interpretation software. The pile body is divided into concentric circular segmented units at a preset depth interval, and the geometric shape of each unit is jointly defined by the pile diameter and the segmented depth. The volume ratios of sandy soil and clay in each segmented unit are calculated by a three-dimensional volume integration algorithm. For example, the volume of sandy soil in the unit accounts for 70% and the clay accounts for 30%, and they are normalized to the soil layer component ratio coefficients, with the sandy soil coefficient being 0.7 and the clay coefficient being 0.3. This process relies on spatial interpolation technology to fill the gaps in the borehole data to ensure the layering accuracy.

[0122] Next, through step 1042, the basic anti-slip parameters of sandy soil and clay are extracted from the interface mechanics database, and the two parameters are linearly weighted and superimposed based on the component ratio coefficients to generate an anti-slip composite parameter adapted to the current segmented unit. The formula for the linear weighted superposition process is as follows: And , where the sandy soil coefficient and the clay coefficient are the values of their proportions in the complex soil mass.

[0123] Secondly, through step 1043, the anti-slip composite parameters generated in step 1042 and their corresponding segmented unit depth positions are arranged in a longitudinal order to form a one-dimensional anti-slip parameter mapping table. The one-dimensional anti-slip parameter mapping table is indexed by depth, and the data structure is a two-dimensional array, reflecting the discrete distribution characteristics of the longitudinal anti-slip ability of the pile body. This process realizes parameter storage and rapid retrieval through a database management tool.

[0124] Again, through step 1044, aiming at the discrete segmentation characteristics of the one-dimensional mapping table, the cubic spline interpolation method is used to non-linearly interpolate the anti-slip composite parameters of adjacent segmented units, and combined with the soil layer transition gradient, such as the slope of the transition zone where sandy soil gradually changes to clay, a continuous anti-slip parameter field is generated to eliminate the parameter mutation between discrete segments.

[0125] Finally, through step 1045, the continuous anti-slip parameter field and the three-dimensional geometric model of the pile body are spatially bound through a finite element modeling tool, and the parameter field is mapped to the grid nodes of the pile-soil interface by using the grid mapping technology. For example, the surface of the pile body is divided into finite element grids, and each node is associated with a corresponding anti-slip parameter value, and a global anti-slip parameter distribution heat map is generated through a visualization engine rendering. This mapping table can be directly imported into the debonding dynamics model to drive the three-dimensional differential simulation of the debonding behavior.

[0126] In practical applications and laboratory simulations, a scaled model pile needs to penetrate an alternating layer of sand and clay with a thickness of about 1.2 m (scaled down by a ratio of 1:10). First, the soil layer profile around the model pile is extracted from CT scan data, and an image analysis software is used to identify the alternating distribution characteristics of sand and clay. The pile body is divided into 24 concentric circular segmented units at a depth interval of 0.05 m. The two-dimensional area integration algorithm is used to calculate the proportion of soil types in each unit. For example, in the unit with a depth of 0.2 - 0.25 m, the sand area proportion is 78.6% and the clay proportion is 21.4%. Bilinear interpolation is used to fill in the missing local data to ensure that the stratification accuracy error is less than 3%. Laboratory-level parameters are extracted from the interface mechanics database: the friction angle of sand is 32° and the cohesion is 5 kPa; the friction angle of clay is 18° and the cohesion is 20 kPa. By linearly superimposing according to the component coefficient, taking the unit of 0.2 - 0.25 m as an example, the composite friction angle is calculated to be 28.7° and the composite cohesion is calculated to be 8.63 kPa, generating the anti-slip parameters for this unit. After calculating each unit one by one, a one-dimensional mapping table is constructed, and the quadratic spline interpolation algorithm is combined with the transition gradient to correct the weight. Taking the interval of 0.25 - 0.3 m in depth as an example, the parameters of adjacent units are 8.63 kPa corresponding to 0.25 m and 11.2 kPa corresponding to 0.3 m. The interpolation function calculates 9.84 kPa at a depth of 0.275 m. Finally, the continuous field is imported into the simplified finite element model. The pile surface is divided into 1,200 quadrilateral grid nodes. After binding the node parameters, a microscopic imaging thermal map is generated, showing the characteristics of higher anti-slip strength in the sand area in the middle of the pile and the strength gradient change in the clay area at the bottom. The simulation results show that the critical debonding load is 12.5 kN, with a deviation of only 2.3% from the laboratory failure test result of 12.8 kN, verifying the high-precision prediction ability of this scheme in complex soil layers.

[0127] The overall scheme of the above 104 realizes the high-precision prediction of the uplift bearing capacity of the slurry mixing pile by dynamically integrating geological data and mechanical parameters. Based on the borehole exploration data, longitudinal segmented units are divided and the soil layer component proportion coefficients are calculated. By linearly superimposing the basic parameters of sand-clay, the anti-slip composite parameters are generated, and a one-dimensional anti-slip parameter mapping table is constructed; further, the non-linear interpolation technology is used to eliminate the mutation error between discrete segments, generating a continuous anti-slip parameter field to accurately characterize the gradient change characteristics of the soil layer transition zone; finally, the global anti-slip parameter distribution map is output through three-dimensional space binding, providing high-resolution input for the debonding dynamics model. This method breaks through the static assumption of the traditional homogenization model, effectively solves the problems of shear force cumulative error caused by interlayer heterogeneity and non-linear characterization of debonding propagation, significantly improves the adaptability to complex soil layer combinations and new slurry ratios, and provides a reliable theoretical support and engineering decision-making basis for the anti-floating design of underground structures.

[0128] 105. Establish an interface debonding dynamics model, input the spatial anti-slip parameter mapping table and the verified deformation gradient characteristics, combine the interlayer blocking effect parameters to simulate the spatial differentiation expansion process of the debonding behavior, and output the evolution data of the correlation between load and depth;

[0129] Optionally, step 105 may specifically include the following steps:

[0130] 1051. Based on the spatial anti-slip parameter mapping table, construct a pile-soil interface mechanical network with segmented units as nodes;

[0131] 1052. Input the verified deformation gradient characteristics into the pile-soil interface mechanical network, calculate the difference between the deformation gradient and the anti-slip composite parameter at each node, and generate the debonding trigger criterion of the node;

[0132] 1053. According to the interlayer blocking effect parameter, a resistance weight of debonding extension between adjacent nodes is defined. If the current node meets the debonding trigger criterion, the extension probability of the debonding to the adjacent node is calculated according to the resistance weight.

[0133] 1054. Using the load monitoring data as a time-series driving signal, iteratively update the debonding state of each node, and when the debonding extends from the surface node to the deep node, record the load value of each deep node when the debonding is triggered;

[0134] 1055. Aggregate the load values and corresponding depths of all nodes when debonding is triggered, and generate the evolution data of the load as the debonding depth increases.

[0135] Among them, step 1055 may specifically include the following processes: traversing all nodes in the pile-soil interface mechanical network, sorting the nodes from shallow to deep according to their depth, and extracting the load value and depth position of each node when debonding is first triggered; performing continuity check on the depth interval between adjacent nodes, and if the depth difference between adjacent nodes exceeds a preset threshold, inserting a virtual node in the interval, and linearly distributing the load value of the preceding node to the virtual node according to the depth difference; integrating the load value and depth of the actual node and the virtual node in the triggering order to generate an initial load depth sequence; detecting the situation where there are multiple load values at the same depth in the initial load depth sequence, retaining the maximum load value and eliminating redundant data points to form a final data point; arranging the final data points in ascending order of depth to generate continuous and monotonic load evolution data with increasing debonding depth.

[0136] In the above solution, the interlayer blocking effect parameter refers to the weight parameter that defines the resistance to debonding expansion due to component differences between adjacent soil layers, including dynamic characteristic quantities such as the resistance coefficient and the energy attenuation factor, and is used to quantify the degree of obstruction and the difficulty of expansion when the debonding behavior crosses different soil layers. The pile-soil interface mechanical network refers to a networked mechanical model with segmented units as nodes. The nodes store the anti-slip parameters and deformation gradient characteristic data corresponding to the segmented sections, and the edges define the soil layer transition relationship and the blocking effect weight between adjacent nodes, and are used to dynamically simulate the spatial expansion path of the debonding behavior. The debonding trigger criterion refers to the difference threshold determination condition of the deformation gradient and the anti-slip composite parameter at the node. If the difference exceeds the critical value, debonding is triggered, indicating the mechanical imbalance state of local interface slip. The virtual node refers to a virtual data point inserted when the depth interval between adjacent actual nodes exceeds the preset threshold, and the load value of the previous node is allocated to the interval through linear interpolation, and is used to fill the discrete gap of the debonding depth evolution data to ensure the continuity and monotonicity of the load-depth curve.

[0137] In the embodiment of the present application, first, based on the spatial anti-slip parameter mapping table in step 1051, the longitudinally continuous segmented units of the pile are abstracted into the nodes of the pile-soil interface mechanical network. Each node corresponds to a specific depth interval of the pile body, and its attributes include the anti-slip parameters and soil layer types of the soil layer within the segmented section. Adjacent nodes are connected by edges, and the attributes of the edges are given the interlayer blocking effect parameters according to the actual soil layer transition type. For example, in the alternating layer of sand and clay, if the sand section of node A is adjacent to the clay section of node B, the blocking weight of edge AB is set to 0.8, indicating the resistance strength of debonding expansion from sand to clay.

[0138] Then, in step 1052, the verified deformation gradient characteristic examples are input into the mechanical network, and the difference between the deformation gradient and the anti-slip composite parameter is calculated for each node. If the difference of a certain node exceeds the preset threshold, it is determined that the node meets the debonding trigger condition. For example, the anti-slip composite parameter of node C is 0.15, the deformation gradient is 0.25% / m, the difference is 0.1, exceeding the threshold of 0.05, then node C is marked as a debonding trigger point.

[0139] Secondly, the debonding expansion rule is defined according to the interlayer blocking effect parameter. If the current node triggers debonding, its adjacent nodes are traversed, and the expansion probability is calculated according to the resistance weight in the edge attributes. For example, when node C expands to node D, the blocking weight of edge CD is 0.6, then the expansion probability is 40%; if the difference of the anti-slip composite parameter of node D does not reach the threshold, the current load increment needs to be superimposed to recalculate its trigger condition. Through probability screening, the range of nodes where debonding may expand in the next iteration step is determined.

[0140] Again, using the collected load monitoring data as the time-series driving signal, update the states of each node in the network iteratively by time step. For example, at the 10th second, the load increases to 150 kN, and node C triggers debonding; at the 15th second, the load increases to 155 kN, and node D triggers debonding because the cumulative expansion probability meets the condition. In each iteration, record the depth of the triggered node and the corresponding load value. For example, when node C triggers, the depth is 3 m and the load is 150 kN, forming a spatio-temporal trajectory of debonding expansion.

[0141] Finally, aggregate the load-depth data of all triggered nodes through step 1055, insert virtual nodes for adjacent nodes with overly large depth intervals, and distribute the load values by linear interpolation. If there are low load values triggered multiple times at the same depth, they are judged as redundant data and removed to generate a continuous and monotonic load-depth evolution curve. For example, if the actual triggered node A has a depth of 1 m and a load of 100 kN, and node B has a depth of 3 m and a load of 140 kN, then a virtual node is inserted at a depth of 2 m to generate an evolution sequence from 1 m to 2 m to 3 m, fully reflecting the progressive relationship between the load and the debonding depth.

[0142] In practical applications, first divide a model pile with a diameter of 30 mm and a height of 1.5 m into 50 longitudinal segmented units based on CT scan data to construct a mechanical network of the pile-soil interface. The node attributes are dynamically assigned according to the laboratory mixture ratio of the soil layer. The friction coefficient of the sand section is 0.25 and the cohesion is 1.2 kPa; the friction coefficient of the clay section is 0.4 and the cohesion is 1.8 kPa. The edges between adjacent nodes in the sand-clay transition zone are given a blocking weight of 0.7, and the weight of the clay-sand transition edge is 0.6. For example, the node at a depth of 0.5 m is in the sand section, and its adjacent node at 0.53 m is in the clay section, and the blocking weight of the edge attribute is set to 0.7. Data is collected through a distributed optical fiber and a micro load cell at the pile top. The deformation monitoring shows that a mutation area appears at a depth of 0.8 m, and the deformation increase rate reaches 0.035% / m. After calibration, it is input into the mechanical network. It is calculated that the anti-slip composite parameter at the 0.8 m node is 0.336 kPa·m, and the deformation gradient difference of 0.014 is greater than the threshold of 0.01, triggering debonding. When traversing adjacent nodes, it expands to the 0.77 m and 0.83 m nodes. Among them, the expansion probability of the 0.77 m node in the sand-clay transition zone is 25%, and the expansion probability of the 0.83 m node in the pure clay section is 35%. In the 3rd iteration when the load increases to 18 kN, the 0.83 m node triggers debonding and the load value of 18.2 kN is recorded. When the load gradually increases to 21 kN, the debonding expands to a depth of 1.1 m, and 2 virtual nodes with an interval of 0.03 m are inserted during this period. The finally generated evolution curve shows that the load increases from 18 kN at 0.8 m to 21 kN at 1.1 m, and the slope change reflects that the resistance increase in the clay section is 22% higher than that in the sand section, with a deviation of 2.3% from the laboratory failure test result of 21.4 kN.

[0143] The overall solution of 105 above realizes the refined prediction of the uplift bearing capacity in complex soil layers by constructing a mechanical network at the pile-soil interface and a dynamic debonding propagation model. First, a segmented unit node network is established based on the spatial anti-slip parameter mapping table, integrating the soil layer heterogeneity parameters and the deformation gradient characteristics to accurately quantify the debonding trigger conditions at each node. The expansion resistance weights of adjacent nodes are defined by the interlayer blocking effect parameters, and combined with the load time-series driving signal, the iterative simulation of the non-linear process of debonding from local trigger to multi-level cascading expansion is carried out, and the load-depth correlation data is dynamically recorded. When further aggregating the debonding trigger point information, a virtual node interpolation and redundant data elimination mechanism is introduced to ensure the continuity and monotonicity of the evolution curve. This method breaks through the static assumption of traditional homogenization models, completely characterizes the blocking effect in the soil layer transition zone and the difference in the debonding spatial expansion path, significantly improves the accuracy of critical load determination, and provides a highly reliable dynamic evolution basis for the uplift design of pile foundations under complex geological conditions.

[0144] 106. Determine the maximum load threshold corresponding to the critical debonding expansion state based on the convergence relationship between the evolution data and the deformation gradient characteristics as the predicted value of the uplift bearing capacity.

[0145] Optionally, step 106 may specifically include the following steps:

[0146] 1061. Extract the increase slope of the load with the debonding depth in the evolution data, and mark the depth point where the direction of the increase slope first reverses as the first critical point;

[0147] 1062. Extract the deformation increase corresponding to the depth of the first critical point in the deformation gradient characteristics. If the deformation increase exceeds a set multiple of the historical average increase, mark it as the second critical point;

[0148] 1063. Record the depth difference between the first critical point and the second critical point. When the depth difference is less than the preset tolerance, determine the load value corresponding to both of them as the maximum load threshold of the critical debonding expansion state. When the depth difference exceeds the preset tolerance, extend the load application duration until a stable point where the load increase is zero appears in the evolution data, and take the last load peak before the stable point as the maximum load threshold, and output the maximum load threshold as the predicted value of the uplift bearing capacity of the pile foundation.

[0149] In the above solution, the maximum load threshold refers to the load characteristic value that reflects the bearing limit of the pile foundation in the critical expansion state of debonding, including the peak characteristics of the load and depth evolution during the debonding expansion process and the dynamic equilibrium state identifier, which can be used as the core basis for predicting the uplift bearing capacity. The first critical point refers to the depth position characteristic where the slope of the load increase rate in the load evolution data first reverses in direction, including the spatial marker of the sudden change in the load transfer path and the slope direction reversal signal, and is used to identify the initial trigger stage of debonding expansion. The second critical point refers to the monitoring position characteristic where the deformation increase corresponding to the depth of the first critical point in the deformation gradient characteristic is significantly abnormal, including the deformation mutation intensity and direction information caused by local debonding, and is used to verify the spatio-temporal correlation between the load mutation and the deformation response. The stable point refers to the depth position characteristic where the load increase rate in the load evolution data is zero and remains stable, including the state identifier of the debonding expansion reaching dynamic equilibrium and the load attenuation convergence signal, and is used to determine the debonding termination stage and correct the maximum load threshold.

[0150] In the embodiment of the present application, first, a continuous curve of the load varying with depth is extracted from the evolution data output by the debonding dynamics model through step 1061, and the load increase rate between adjacent depth points is calculated using the sliding window difference algorithm. Specifically, the window length is set to 3 depth sampling points. The initial slope is calculated for the first two points within the window, and the subsequent slope is calculated for the last two points. When the first reversal of the slope direction within the window is detected, the depth of the center point of the window is marked as the first critical point. For example, if the initial slope within a certain window is +8 kN / m and the subsequent slope is -3 kN / m, then the depth of 8.6 m corresponding to this window is determined as the first critical point, indicating that the load transfer path mutates due to the trigger of debonding here.

[0151] Secondly, based on the depth position of the first critical point, the deformation increase value corresponding to this depth is extracted from the deformation gradient characteristic. The historical average increase of this depth point is calculated through sliding time window mean filtering. If the current deformation increase exceeds a set multiple of the historical mean, it is determined as the second critical point. For example, if the historical mean is 0.15 mm / m, the current deformation increase is 0.4 mm / m, and the set multiple is 2, then the second critical point marker is triggered. This step verifies the correlation between the load mutation and the deformation mutation through spatio-temporal matching, avoiding misjudgment caused by local noise.

[0152] Finally, calculate the depth difference between the first critical point and the second critical point through step 1063. If the difference is less than the preset tolerance, determine that the load value corresponding to both of them is the maximum threshold; if it exceeds the tolerance, extend the load application time and continuously monitor the evolution data until a stable point where the load increase rate becomes zero is detected. At this time, extract the last load peak before the stable point as the corrected maximum threshold, and output the maximum load threshold as the predicted value of the uplift bearing capacity of the pile foundation. For example, if the depth of the first critical point is 8.6 m, the second critical point is 9.3 m, and the depth difference is 0.7 m, continue to load until the load increase rate approaches zero, and select the peak value of 1250 kN before the stable point as the final predicted value. This process ensures that the threshold determination takes into account the spatio-temporal consistency of load deformation and the final state equilibrium characteristics of debonding expansion through a dynamic iterative correction mechanism.

[0153] In practical applications, extract the load-depth curve from the evolution data output by the debonding dynamics model at a sampling interval of 0.02 m, and use the sliding window difference algorithm with a window length of 5 points to calculate the slope. For example, in the depth range of 0.84 - 0.90 m, the loads corresponding to the first two points of 0.84 m and 0.86 m are 10.5 kN and 11.2 kN respectively, and the initial slope is calculated as +35 kN / m; the loads corresponding to the last two points of 0.88 m and 0.90 m are 11.0 kN and 10.7 kN respectively, and the subsequent slope is calculated as -15 kN / m. Since the slope direction changes from positive to negative, determine that the center point of the window, 0.86 m, is the first critical point, indicating that the load transfer path mutation is triggered by the debonding of the clay layer here. Subsequently, extract the deformation increase data at a depth of 0.86 m from the deformation gradient characteristics, and through the sliding time window mean filtering, calculate the historical average deformation increase at this point as 0.018 mm / m with a monitoring period of 50 groups in the window length. The deformation increase in the current monitoring period reaches 0.052 mm / m, exceeding twice the threshold of 0.036 mm / m, triggering the second critical point marker, verifying the spatio-temporal correlation between load mutation and deformation mutation, and excluding misjudgment caused by equipment vibration noise. Then calculate the depth difference between the first critical point and the second critical point as 0.03 m, which is less than the preset tolerance of 0.05 m, and directly determine that the load value of 11.5 kN corresponding to both of them is the maximum threshold, and output the maximum threshold as the predicted value of the uplift bearing capacity of the pile foundation. In another set of tests, the first critical point is 0.92 m, corresponding to a deformation increase of 0.048 mm / m, the second critical point is marked as 0.99 m, and the depth difference of 0.07 m exceeds the tolerance. The system automatically extends the load application time by 1.5 minutes, monitors that the load increase rate becomes zero at a depth of 1.08 m, extracts the peak value of 12.8 kN before the stable point as the corrected maximum threshold, and outputs it as the predicted value of the uplift bearing capacity of the pile foundation.

[0154] The overall solution of the above 106 realizes the accurate determination of the critical debonding expansion state through the collaborative analysis of load evolution data and deformation gradient characteristics. First, the first critical point is identified based on the reversal of the load increase slope direction to locate the initial mutation position of debonding triggering; second, the second critical point is verified by comparing the deformation increase with the historical mean threshold to ensure the spatio-temporal correlation of the load-deformation mutation; finally, combined with the depth difference tolerance determination and the stable point iterative correction mechanism, the nonlinear process of debonding expansion is dynamically adapted. This method breaks through the limitations of traditional models that rely on static superposition and empirical coefficients. Through multi-source data fusion and dynamic parameter correction, it effectively characterizes the blocking effect of interlayer heterogeneity on debonding behavior, avoiding error accumulation caused by homogenization assumptions; at the same time, it completely restores the dynamic path of debonding from local triggering to multi-stage expansion, accurately captures the mutation characteristics of the critical state, significantly improves the adaptability to complex soil layer combinations and new slurry ratios, and finally outputs the predicted value of the uplift bearing capacity with both theoretical rationality and engineering verification, providing high-reliability support for the anti-floating design of underground structures.

[0155] The following is a complete example for steps 101 to 106, as Figure 2 shown. First, when preparing a sand-clay alternating layered composite soil sample in the laboratory, a precision layered compaction device is used to construct a cylindrical sample with a diameter of 200 mm and a height of 400 mm with an accuracy of ±0.1 mm. The sand layer and the clay layer are alternately laid with an equal thickness of 30 mm. Four ratios of cement-bentonite slurry are injected through a high-pressure grouting system to form a simulated solidified pile body with a diameter of 30 mm. A laser profilometer is used to perform three-dimensional topography scanning on the solidification interface, and geometric parameters such as the interface undulation height, effective contact area ratio, and fractal dimension are extracted through an image processing algorithm. Simultaneous micro-focus CT scanning shows that when the water-solid ratio is 1.0, the penetration depth of the slurry in the sand layer reaches 22 mm, while in the clay layer, it only penetrates 2.8 mm due to porosity limitations. At this time, the interface contact area ratio reaches a peak of 82%.

[0156] During the interface mechanical property testing stage, a multi-mode loading was applied to the composite specimens using an electronic universal testing machine. When conducting the tensile test with an axial load applied at a rate of 0.1 mm / s, a bimodal load-displacement curve was captured by a laser displacement sensor at a sampling rate of 100 Hz. The first peak of the curve, ranging from 0.5 - 1.8 MPa, corresponds to the bond failure of the clay slurry interface, and the second peak, ranging from 1.2 - 2.6 MPa, reflects the frictional energy dissipation of the sand slurry interface. Based on the Mohr-Coulomb criterion, the friction angle range of the sand interface was calculated to be 29° - 34° from the sliding resistance curve in the post-separation stage, which is significantly higher than the friction angle range of the clay interface (18° - 22%). The established mechanical database contains 80 sets of structured data. Each record is associated with 5 geometric parameters, namely interface undulation height, contact area ratio, fractal dimension, penetration depth, penetration uniformity, 3 mechanical parameters, namely tensile strength, friction angle, residual strength, and 2 material ratio parameters, namely water-solid ratio and bentonite content. The data is stored in JSON format to achieve rapid retrieval of multi-dimensional parameters.

[0157] The deformation monitoring system is composed of a 32-channel strain acquisition instrument and an LVDT displacement sensor networked together. A strain gauge array is arranged on the surface of the simulated pile body at intervals of 50 mm. When the axial load is applied up to 12 kN, a strain mutation is detected in the area with a depth of 120 - 150 mm through wavelet transform. Its axial strain gradient reaches 0.08% / mm, which is 3.2 times the baseline value, and the radial shrinkage rate suddenly increases by 1.8 times. The dynamic time warping algorithm is used to align the load and deformation time series data, and 3 abnormal data segments caused by sensor temperature drift are removed. Finally, a calibration data set with a correlation coefficient greater than 0.91 is obtained. Based on the layered soil model reconstructed by CT scanning, the volume weighted method is used to calculate the anti-slip parameters of each depth unit.

[0158] When establishing the discretized pile-soil interface model, the 400-mm pile length is divided into 40 nodes at intervals of 10 mm, and each node is assigned an initial anti-slip strength. When the local shear stress is greater than or equal to the initial anti-slip strength, the debonding state is triggered. The numerical simulation shows that the initial debonding occurs at the shallow nodes with a depth of 20 mm, and then it expands downward at a rate of 0.5 mm / kN. However, it encounters a blockage in the clay-dominated layer, that is, at a depth of 90 - 120 mm, and an additional load of 4 kN is required to break through the interface resistance. By inserting virtual nodes, the spatial resolution is increased to 2 mm, and the obtained load-depth evolution curve shows three stages: a linear elastic stage, a non-linear transition stage, and a critical instability stage. When the load reaches 22.3 kN, an inflection point of the evolution curve and a sudden increase in strain of 0.12% / mm occur simultaneously at a depth of 85 mm. The spatial deviation between the two critical points is only 0.6 mm, which is less than the preset tolerance. Based on this, the anti-pulling bearing capacity threshold is determined to be 22.3 kN, and the error from the measured value of 23.1 kN in the physical test is controlled within 3.5%.

[0159] When verifying the reliability of the method, 5 repeated tests were carried out on specimens with the same ratio, and the standard deviation of the bearing capacity was measured to be 0.7 kN. Moreover, the correlation coefficient between the interfacial fractal dimension and the debonding trigger load reached 0.89. Sensitivity analysis shows that when the anti-slip parameter error is ±10%, the predicted value of the bearing capacity fluctuates by ±8%. It is necessary to control the quality of the input parameters through CT scanning with an error less than ±2%.

[0160] Figure 3 The following is a schematic structural diagram of a prediction system for the uplift bearing capacity of a slurry mixing pile provided by an embodiment of the present application, as Figure 3 shown. The system includes:

[0161] An acquisition module 31, which acquires the geometric characteristic parameters of the interface structure formed by the solidified slurry in multi-layer heterogeneous soil layers under different ratios;

[0162] The acquisition module 31 further includes measuring the interfacial mechanical parameters of the multi-layer heterogeneous soil layers through mechanical tests, and constructing an interfacial mechanical database in combination with the geometric characteristic parameters;

[0163] A calibration module 32, which collects the pile body deformation monitoring data and the load monitoring data, generates a deformation gradient feature by identifying the deformation mutation threshold, and performs collaborative calibration on the load monitoring data and the deformation gradient feature;

[0164] A generation module 33, which divides the pile body into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layers, adjusts the anti-slip parameters in the interfacial mechanical database based on the soil layer component ratio within each segmented unit, and generates a spatial anti-slip parameter mapping table;

[0165] An evolution module 34, which establishes an interfacial debonding dynamics model, simulates the spatially differentiated expansion process of the debonding behavior by inputting the spatial anti-slip parameter mapping table and the calibrated deformation gradient feature, and combines the interlayer blocking effect parameters, and outputs the evolution data related to the load and depth;

[0166] A prediction module 35, which determines the maximum load threshold corresponding to the critical debonding expansion state as the predicted value of the uplift bearing capacity based on the convergence relationship between the evolution data and the deformation gradient feature.

[0167] Figure 3 The above prediction system for the uplift bearing capacity of a slurry mixing pile can execute Figure 1 the prediction method for the uplift bearing capacity of a slurry mixing pile described in the embodiment shown. The implementation principle and technical effects will not be elaborated again. For the prediction system for the uplift bearing capacity of a slurry mixing pile in the above embodiment, the specific ways for each module and unit to execute operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0168] In a possible design,Figure 3 A prediction system for the uplift bearing capacity of a slurry mixing pile according to the illustrated embodiment can be implemented as a computing device, such as Figure 4 As shown, the computing device may include a storage component 41 and a processing component 42;

[0169] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42.

[0170] The processing component 42 is used for the above Figure 1 A prediction method for the uplift bearing capacity of a slurry mixing pile according to the illustrated embodiment.

[0171] Among them, the processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0172] The storage component 41 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0173] Of course, the computing device may also necessarily include other components, such as an input / output interface, a display component, a communication component, etc.

[0174] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0175] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0176] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0177] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the aboveFigure 1 A method for predicting the uplift bearing capacity of a slurry mixing pile in the illustrated embodiment.

[0178] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0179] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0180] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A prediction method for the uplift bearing capacity of slurry mixing piles, characterized in that Including: Obtaining geometric characteristic parameters of the interface structure formed by the solidified grout in multi-layer heterogeneous soil layers under different ratios; Measuring the interface mechanical parameters of the multi-layer heterogeneous soil layers through mechanical tests, and constructing an interface mechanical database in combination with the geometric characteristic parameters; Collecting pile deformation monitoring data and load monitoring data, generating deformation gradient characteristics by identifying deformation mutation thresholds, and performing collaborative verification on the load monitoring data and the deformation gradient characteristics; Dividing the pile body into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layers, adjusting the anti-slip parameters in the interface mechanical database based on the soil layer component ratios in each segmented unit, and generating a spatial anti-slip parameter mapping table; Establishing an interface debonding dynamics model, by inputting the spatial anti-slip parameter mapping table and the verified deformation gradient characteristics, and combining with the interlayer blocking effect parameters to simulate the spatially differentiated expansion process of the debonding behavior, and outputting the evolution data of the load-depth correlation; Based on the convergence relationship between the evolution data and the deformation gradient characteristics, determining the maximum load threshold corresponding to the debonding critical expansion state as the predicted value of the uplift bearing capacity.

2. The method according to claim 1, characterized in that, Collecting pile deformation monitoring data and load monitoring data, generating deformation gradient characteristics by identifying deformation mutation thresholds, and performing collaborative verification on the load monitoring data and the deformation gradient characteristics, including: Synchronously collecting multi-dimensional deformation monitoring data on the surface of the pile body and load monitoring data at the pile top at fixed time intervals; Performing continuous spatial scanning on the deformation monitoring data, positioning adjacent regions with sudden changes in deformation values as mutation regions, extracting the deformation increase amplitude and direction change angle of the mutation regions, and generating a set of deformation mutation thresholds; According to the extreme points of the increase amplitude in the set of deformation mutation thresholds, dividing the deformation gradient intervals longitudinally along the pile body, calculating the change rate of the deformation increase amplitude with depth in each deformation gradient interval, and generating deformation gradient characteristics; Performing event synchronization matching on the load monitoring data according to the acquisition timestamp and the generation timestamp of the deformation gradient characteristics, and screening out the synchronous change intervals of the load increase amplitude and the deformation gradient increase amplitude; Performing amplitude ratio verification on the load data and the deformation gradient characteristics in the synchronous change interval, and if the ratio of the load increase amplitude to the deformation gradient increase amplitude exceeds the preset fluctuation range, removing the abnormal data segment and outputting the verified deformation gradient characteristics.

3. The method according to claim 1, wherein Dividing the pile body into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layers, adjusting the anti-slip parameters in the interface mechanical database based on the soil layer component ratios in each segmented unit, and generating a spatial anti-slip parameter mapping table, including: Extracting the longitudinal distribution profile of the soil layer around the pile according to the borehole exploration data, dividing the pile body into multiple concentric annular segmented units at preset depth intervals, calculating the volume ratios of sand and clay inside each segmented unit, and converting the volume ratios into soil layer component ratio coefficients; Extracting the basic anti-slip parameters corresponding to sand and clay from the interface mechanical database, linearly superimposing the basic anti-slip parameters corresponding to sand and clay respectively according to the soil layer component ratio coefficients, and generating an anti-slip composite parameter adapted to the current segmented unit; Arrange the depth position of each segment unit and the corresponding anti-slip composite parameter in a longitudinal order to form a one-dimensional anti-slip parameter mapping table with depth as the index; Based on the one-dimensional anti-slip parameter mapping table, the anti-slip composite parameters of adjacent segmented units are nonlinearly interpolated according to the soil layer transition gradient to generate a continuous anti-slip parameter field; The continuous anti-slip parameter field is spatially bound to the three-dimensional geometric model of the pile body, and a global anti-slip parameter distribution map of the pile-soil interface is output as a spatial anti-slip parameter mapping table.

4. The method according to claim 1, characterized in that, Establish an interface debonding dynamics model, input the spatial anti-slip parameter mapping table and the verified deformation gradient characteristics, combine the interlayer blocking effect parameters to simulate the spatial differentiation expansion process of debonding behavior, and output the evolution data of load and depth correlation, including: Based on the spatial anti-slip parameter mapping table, a pile-soil interface mechanical network with segmented units as nodes is constructed; Inputting the verified deformation gradient characteristics into the pile-soil interface mechanical network, calculating the difference between the deformation gradient and the anti-slip composite parameter at each node, and generating the debonding trigger criterion of the node; According to the interlayer blocking effect parameter, the resistance weight of the debonding extension between adjacent nodes is defined. If the current node meets the debonding trigger criterion, the probability of the debonding extending to the adjacent node is calculated according to the resistance weight; Using the load monitoring data as a time-series driving signal, iteratively update the debonding state of each node, and when the debonding extends from the surface node to the deep node, record the load value of each deep node when the debonding is triggered; The load values and their corresponding depths when debonding is triggered at all nodes are aggregated to generate the evolution data of the load as the debonding depth increases.

5. The method according to claim 4, wherein Aggregate the load values and corresponding depths of all nodes when debonding is triggered, and generate the evolution data of the load as the debonding depth increases, including: Traversing all nodes in the pile-soil interface mechanical network, sorting the nodes from shallow to deep according to their depth, and extracting the load value and depth position of each node when debonding is first triggered; The depth intervals between adjacent nodes are checked for continuity. If the depth difference between adjacent nodes exceeds a preset threshold, a virtual node is inserted into the interval and the load value of the previous node is linearly distributed to the virtual node according to the depth difference. Integrate the load values and depths of the actual nodes and the virtual nodes in a triggering order to generate an initial load depth sequence; Detecting the presence of multiple load values at the same depth in the initial load depth sequence, retaining the maximum load value and removing redundant data points to form a final data point; The final data points are arranged in order of increasing depth to generate continuous and monotonic load evolution data with increasing debonding depth.

6. The method according to claim 1, characterized in that Based on the convergence relationship between the evolution data and the deformation gradient characteristics, the maximum load threshold corresponding to the critical extension state of debonding is determined as the prediction value of the pull-out bearing capacity, including: Extracting the increase slope of the load changing with the debonding depth in the evolution data, and marking the depth point where the increase slope reverses direction for the first time as the first critical point; Extracting the deformation increase corresponding to the depth of the first critical point from the deformation gradient feature, and marking it as the second critical point if the deformation increase exceeds a set multiple of the historical average increase; Record the depth difference between the first critical point and the second critical point. When the depth difference is less than the preset tolerance, determine that the load value corresponding to both of them is the maximum load threshold of the debonding critical expansion state. When the depth difference exceeds the preset tolerance, extend the load application duration until a stable point with zero load increase appears in the evolution data, and use the last load peak before the stable point as the maximum load threshold, and output the maximum load threshold as the predicted value of the uplift bearing capacity of the pile foundation.

7. The method according to claim 1, wherein Determine the interface mechanical parameters of the multi-layer heterogeneous soil layer through mechanical tests, and construct an interface mechanical database in combination with the geometric characteristic parameters, including: Prepare a composite soil sample containing alternating layers of sand and clay, and embed a solidified slurry in the composite soil sample to form a simulated pile-soil interface; Apply multi-level tensile loads to the simulated pile-soil interface, monitor the load values and displacement amounts during the interface separation process, and extract the peak points of the load-displacement curve as the interface tensile strength; After the interface is completely separated, measure the frictional sliding resistance of the separation surface, and calculate the interface friction angle according to the change relationship between the sliding displacement and the frictional sliding resistance; Extract the surface undulation height and the contact area ratio of the simulated pile-soil interface to generate a set of geometric characteristic parameters; Match the interface tensile strength with the set of interface friction angles under each group of ratios to establish interface mechanical parameters indexed by the ratio number; Aggregate the set of geometric characteristic parameters and the interface mechanical parameters under all ratio numbers to generate an interface mechanical database containing the mapping relationship between ratio, geometry and mechanics.

8. A prediction system for the uplift bearing capacity of slurry mixing piles, characterized in that, Including: An acquisition module that acquires the geometric characteristic parameters of the interface structure formed by the solidified slurry in the multi-layer heterogeneous soil layer under different ratios; The acquisition module further includes determining the interface mechanical parameters of the multi-layer heterogeneous soil layer through mechanical tests, and constructing an interface mechanical database in combination with the geometric characteristic parameters; A verification module that collects pile deformation monitoring data and load monitoring data, generates a deformation gradient feature by identifying the deformation mutation threshold, and performs collaborative verification on the load monitoring data and the deformation gradient feature; A generation module that divides the pile body into longitudinally continuous segmented units according to the spatial distribution characteristics of the soil layer, adjusts the anti-slip parameters in the interface mechanical database based on the soil layer component ratio in each segmented unit, and generates a spatial anti-slip parameter mapping table; An evolution module that establishes an interface debonding dynamics model, inputs the spatial anti-slip parameter mapping table and the verified deformation gradient feature, and simulates the spatially differentiated expansion process of the debonding behavior in combination with the interlayer blocking effect parameters, and outputs the evolution data related to the load and depth; A prediction module that determines the maximum load threshold corresponding to the debonding critical expansion state as the predicted value of the uplift bearing capacity based on the convergence relationship between the evolution data and the deformation gradient feature.

9. A computing device, characterized in that, Including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for predicting the uplift bearing capacity of a slurry mixing pile as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, A computer program is stored, and when the computer program is executed by a computer, it implements a method for predicting the uplift bearing capacity of a slurry mixing pile as described in any one of claims 1 to 7.

Images