Cooperative early warning method, system and equipment for deformation stress of soft soil around pile and medium

Abstract

The invention provides a cooperative early warning method, system, equipment and medium for deformation stress of soft soil around a pile, and relates to the technical field of underground engineering, and the method comprises the steps that monitoring data of the soft soil around the pile are obtained based on monitoring points, and the monitoring points comprise pile body monitoring points and soil body monitoring points; feature extraction is conducted on the monitoring data, and monitoring indexes reflecting pile periphery soft soil deformation and stress evolution are obtained based on information contribution degree difference and sensitivity selection; performing model construction based on the monitoring data and the monitoring indexes, and obtaining a deformation-stress collaborative map of the soft soil around the pile by considering risk assessment and spatial heterogeneity; and on the basis of the deformation-stress collaborative atlas, abnormal recognition of the soft soil around the pile is carried out, an abnormal area is obtained through embedded learning and clustering analysis, graded early warning is carried out according to the abnormal area, and an early warning result of the soft soil around the pile is obtained. The problem that an existing early warning method for the soft soil around the pile lacks dynamic sensing and combined early warning in the pile-soil interaction process is solved.

Description

Technical Field

[0001] The present invention relates to the field of underground engineering technology, and in particular to a method, system, equipment and medium for collaborative early warning of soft soil deformation stress around a pile. Background Art

[0002] In underground engineering, pile foundations are often used in soft soil areas to enhance the bearing capacity and stability of the foundation. However, under the long-term operation of infrastructure such as railways or extreme loads (such as train loads, heavy rain, and earthquakes), the soft soil around the piles is prone to cumulative deformation and reduced strength, causing the piles to tilt, sink, and even lead to structural instability.

[0003] Current railway health monitoring methods mostly focus on the structure itself (such as pile strain and displacement) or overall soil settlement, but lack dynamic perception and joint early warning mechanisms for pile-soil interaction processes. Traditional methods have the following limitations: They monitor only a single indicator (stress or deformation) in the pile or soil, failing to reflect the coupling relationship between soft soil deformation and stress changes in real time. Furthermore, the deformation and stress of the soft soil surrounding the pile exhibit significant spatial heterogeneity (e.g., vertical settlement propagates layer by layer, and horizontal stress decays radially). Existing technologies typically treat monitoring points as independent units without constructing a mechanical correlation model between these nodes, making it difficult to identify the spatial diffusion patterns of localized abnormal regions. Furthermore, existing methods often issue warnings based on out-of-limit indicators at a single monitoring point, making it difficult to link discrete abnormal points into physically meaningful continuous regions. This hinders engineers from quickly locating risk sources.

[0004] Therefore, there is an urgent need for a collaborative early warning method that takes into account the coupling relationship between soft soil deformation and stress changes, as well as the spatial heterogeneity of deformation and stress of soft soil around piles, to achieve dynamic perception and joint early warning of the pile-soil interaction process, and to obtain accurate early warning results of soft soil around piles. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, system and device for collaborative early warning of deformation and stress of soft soil around piles to improve the above-mentioned problems. To achieve the above-mentioned purpose, the technical solutions adopted by the present invention are as follows:

[0006] In a first aspect, the present application provides a collaborative early warning method for soft soil deformation and stress around piles, comprising:

[0007] Acquiring monitoring data of soft soil around the pile based on monitoring points, the monitoring data including pile deformation data, pile stress data, soil deformation data, soil stress data and environmental data, the monitoring points including pile monitoring points and soil monitoring points;

[0008] Feature extraction is performed on the monitoring data. Based on the difference in information contribution and sensitivity selection, monitoring indicators reflecting the deformation and stress evolution of the soft soil around the pile are obtained.

[0009] Based on the monitoring data and monitoring indicators, a model is constructed, and by considering risk assessment and spatial heterogeneity, a deformation-stress synergy map of the soft soil around the pile is obtained;

[0010] Abnormal identification of soft soil around piles is performed based on the deformation-stress collaborative map. Abnormal areas are obtained through embedding learning and cluster analysis. Graded warnings are performed based on the abnormal areas to obtain the early warning results of soft soil around piles.

[0011] Secondly, the present application also provides a collaborative early warning system for soft soil deformation and stress around piles, comprising:

[0012] an acquisition unit, configured to acquire monitoring data of the soft soil around the pile based on monitoring points, the monitoring data including pile deformation data, pile stress data, soil deformation data, soil stress data, and environmental data, the monitoring points including pile monitoring points and soil monitoring points;

[0013] The feature extraction unit is used to extract features from the monitoring data and obtain monitoring indicators reflecting the deformation and stress evolution of the soft soil around the pile based on the difference in information contribution and sensitivity selection;

[0014] The construction unit is used to construct a model based on monitoring data and monitoring indicators, and obtain the deformation-stress synergy map of the soft soil around the pile by considering risk assessment and spatial heterogeneity;

[0015] The early warning unit is used to identify abnormalities in soft soil around piles based on the deformation-stress collaborative map. The abnormal areas are obtained through embedding learning and cluster analysis, and graded early warnings are performed based on the abnormal areas to obtain early warning results for soft soil around piles.

[0016] In a third aspect, the present application also provides a collaborative early warning device for soft soil deformation and stress around piles, comprising:

[0017] memory for storing computer programs;

[0018] A processor is used to implement the steps of the collaborative early warning method for soft soil deformation and stress around piles when executing the computer program.

[0019] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned collaborative early warning method based on deformation and stress of soft soil around piles.

[0020] The beneficial effects of the present invention are as follows: the present invention pre-processes and extracts features from multi-source monitoring data of soft soil around piles, screens out monitoring indicators that reflect soil deformation and stress evolution, and realizes dynamic quantification and effective tracking of the soil state around the pile. Combining the mechanical response prediction value with the monitoring data, a complete risk factor input space is constructed to enhance the depth and generalization ability of the model, laying the foundation for risk assessment. Based on the engineering structure logic, a deformation-stress collaborative map is constructed, and embedded learning is performed using a graph neural network to capture the spatial collaborative characteristics of soil deformation and stress. Accurate identification and graded warning of abnormal areas are achieved through node anomaly calculation and cluster analysis. The method of the present invention enhances the accuracy of anomaly identification and the practicality of warning, provides a scientific and real-time risk warning means for the safety monitoring of soft soil around piles, improves engineering safety assurance and management efficiency, and has good application and promotion value.

[0021] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 Schematic diagram of the process of the coordinated early warning method for deformation and stress of soft soil around piles according to an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of pile soil in an embodiment of the present invention;

[0025] Figure 3 Schematic diagram of the structure of the soft soil deformation stress collaborative early warning system around piles according to an embodiment of the present invention;

[0026] Figure 4 Schematic diagram of the structure of the coordinated early warning device for soft soil deformation stress around piles described in an embodiment of the present invention.

[0027] Markings in the figure: 901, acquisition unit; 902, feature extraction unit; 903, construction unit; 904, early warning unit; 800, collaborative early warning equipment for soft soil deformation and stress around piles; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0030] Example 1:

[0031] This embodiment provides a collaborative early warning method for soft soil deformation and stress around piles.

[0032] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, and step S4.

[0033] Step S1: Acquire monitoring data of soft soil around the pile based on monitoring points, wherein the monitoring data includes pile deformation data, pile stress data, soil deformation data, soil stress data, and environmental data. The monitoring points include pile monitoring points and soil monitoring points.

[0034] In this embodiment, multiple monitoring points are selected to provide early warning for the soft soil area around the pile. This is due to the spatial heterogeneity of the soft soil area around the pile and the locality of the pile-soil interaction. The mechanical parameters of soft soil (such as compression modulus, shear strength, porosity, etc.) often show significant variability in space. Even in the same area, the soil strength, moisture content, settlement rate, etc. at different locations may be different. Single-point data cannot reflect these spatial differences. At the same time, the stress transfer and deformation effects of the pile foundation on the soft soil around it are locally attenuated. Therefore, single-point monitoring is difficult to reflect the health status of the global pile-soil system.

[0035] The step S1 comprises:

[0036] Step S11: setting a monitoring area for the pile foundation and arranging multiple monitoring points based on the monitoring area;

[0037] In this embodiment, a monitoring range is defined within the pile foundation and the surrounding soft soil area, based on project requirements and the distribution of the pile foundation structure. Pile body and soil monitoring points are strategically located based on the geological conditions, pile foundation type, and load distribution characteristics of the monitoring area to achieve spatially distributed monitoring of the pile-soil system. Monitoring points should be located at varying depths and horizontal locations to ensure representative and complete monitoring data.

[0038] Step S12: collecting pile deformation data and pile stress data of the pile foundation based on the pile monitoring points, wherein the pile deformation data includes pile horizontal displacement, pile vertical displacement and pile strain, and the pile stress data includes pile axial stress and pile shear stress;

[0039] In this embodiment, monitoring sensors (such as fiber optic sensors, strain gauges, and displacement meters) installed on the inner surface of the pile body collect information on the deformation and stress generated during operation. The horizontal displacement of the pile body reflects lateral deformation due to stress, the vertical displacement of the pile body reflects vertical settlement, the strain of the pile body reflects local stress concentration or damage, the axial stress of the pile body represents longitudinal load transfer, and the shear stress of the pile body reflects the relationship between lateral slip and soil interaction.

[0040] Step S13: collecting soil deformation data and soil stress data of the soft soil around the pile based on the soil monitoring points, wherein the soil deformation data includes vertical settlement and horizontal displacement of the soft soil around the pile, and the soil stress data includes soil pressure, pore water pressure and soil strain;

[0041] In this embodiment, the vertical settlement and horizontal displacement of the soft soil around the pile reflect the overall sinking trend of the foundation and the deformation and expansion of the soft soil around the pile in the lateral direction, respectively.

[0042] Step S14: Acquire environmental data based on the monitoring points, the environmental data including temperature and groundwater level.

[0043] In this embodiment, environmental factors have a significant impact on the mechanical properties of soft soil. For example, temperature affects the physical state and material properties of the soil, and groundwater level affects pore pressure changes, effective stress state, and soil strength. It plays a dominant role in the soft soil response, especially during heavy rain or seasonal changes. Therefore, it is necessary to synchronously collect environmental data for subsequent model calibration and anomaly interpretation.

[0044] This step also pre-processes the collected pile deformation data, pile stress data, soil deformation data, soil stress data and environmental data to obtain monitoring data. Specifically, since different sensors (such as pile strain gauges, soil pressure sensors, and groundwater level gauges) may have different sampling frequencies or time lags, all data need to be aligned to a unified time base, and interpolation, resampling, or sliding window averaging methods are used to ensure that all types of data are comparable at the same time node. At the same time, due to the irregular spatial distribution, their spatial coordinates need to be standardized, a coordinate index needs to be constructed, or they need to be mapped to a standard reference system based on a geographic / engineering coordinate system (such as pile number + depth) to facilitate the subsequent establishment of a deformation-stress collaborative map.

[0045] like Figure 2 The following is a schematic diagram of pile soil. Figure 2 The soil properties are given in the text. Soil layers at different depths have different characteristics, so the data collected will be different. Figure 2 The pile shown is a conventional straight pile with a length of 4000 cm and a diameter of 160 cm. Twenty strain gauges are placed on the pile surface at eight cross sections to collect pile stress data. Corresponding strain gauges are also placed on the pile surface to collect pile deformation data. Earth pressure sensors and groundwater level gauges are also placed in the soil.

[0046] At the same time, data cleaning and repair are also carried out to eliminate or fill in missing values ​​caused by equipment failure and communication interruption, and to correct or eliminate abnormal mutation points (such as jumps caused by sensor drift). Sliding median filtering or Z-score detection can be used, and all data are physically consistent (for example, settlement cannot be negative and pore pressure should be within a reasonable range).

[0047] Because different data dimensions have different scales, their numerical ranges and units vary significantly. If raw data is used directly for subsequent correlation analysis or score calculations, indicators with larger scales will have a dominant influence on the calculation process, such as the Pearson correlation coefficient and weighted score, leading to an imbalance in indicator selection. Therefore, the processed data is normalized (using Min-Max normalization or Z-score standardization).

[0048] After the above steps, the collected pile deformation data, pile stress data, soil deformation data, soil stress data and environmental data are integrated into a unified data structure in time and space to obtain monitoring data.

[0049] Step S2: Extract features from the monitoring data and obtain monitoring indicators reflecting the deformation and stress evolution of the soft soil around the pile based on information contribution differences and sensitivity selection;

[0050] In this embodiment, the acquired monitoring data is high-dimensional, redundant, and heterogeneous, with information duplication and differences in information contribution between the data. Therefore, relevant indicators are extracted. Different indicators contribute differently to the pile-soil interaction state. Therefore, feature selection is used to extract a set of monitoring indicators that are most sensitive and representative of the coupled evolution of deformation and stress.

[0051] In step S2, the steps for obtaining the monitoring indicators are:

[0052] Step S21: constructing a first candidate indicator through monitoring data, wherein the first candidate indicator includes a plurality of candidate feature indicators;

[0053] In this embodiment, the first candidate indicator is a potential sensitive indicator reflecting the coupled deformation-stress-environment evolution process of the soft soil area around the pile, and is obtained through preprocessed soil deformation data, soil stress data and environmental data.

[0054] Candidate characteristic indicators based on soil deformation data include the vertical cumulative settlement of the monitoring point, the horizontal cumulative displacement, the daily settlement increment, the displacement change rate, the coefficient of variation of the settlement / horizontal displacement change, the deformation ratio at different depths (such as the surface / deep settlement ratio), and the ratio of the surface horizontal displacement to the pile top displacement.

[0055] Candidate characteristic indicators based on soil stress data include soil pore water pressure, pore pressure change rate, vertical effective stress, horizontal effective stress, effective stress ratio, stress path offset (initial-current), and stress change fluctuation amplitude (standard deviation).

[0056] Candidate characteristic indicators based on environmental data include soil temperature change amplitude, groundwater level change amplitude, daily rainfall, and settlement change within 1 day after rainfall.

[0057] It also includes candidate characteristic indicators constructed based on multiple data, including the correlation coefficient between soil displacement and pore pressure, water level-pore pressure ratio, pore pressure recovery coefficient (after drainage or rainfall), settlement-stress delay time, multi-point settlement synergy coefficient, and the angle between the main displacement direction and the pile center line.

[0058] The extracted multiple candidate characteristic indicators are taken as the first candidate indicators, which cover the soft soil deformation response characteristics, stress and pore pressure state evolution, environmental disturbance effects and multimodal coupling behavior patterns.

[0059] Step S22: Calculate the Pearson correlation coefficient matrix between multiple candidate feature indicators using the first candidate indicator to obtain the Pearson correlation coefficient between every two candidate feature indicators;

[0060] In this embodiment, multiple candidate characteristic indicators are extracted from monitoring data such as soil settlement, stress, pore pressure, displacement, temperature, and water level. Although these indicators can reflect information from different angles, there are highly correlated redundant indicators. If used directly, the information weight will be offset and the real key influencing factors will be obscured. Therefore, it is necessary to use the Pearson correlation coefficient matrix to evaluate the linear correlation between the indicators and eliminate highly redundant indicators to improve the efficiency and accuracy of subsequent analysis.

[0061] In this step, the n candidate feature indicators are grouped into a set of multidimensional vectors, forming an m×n indicator matrix, where m represents the number of samples. The Pearson correlation coefficient is calculated for any two columns in the indicator matrix to obtain the Pearson correlation coefficient between any two candidate feature indicators.

[0062] Step S23: eliminating redundancy from multiple candidate feature indicators using the Pearson correlation coefficient to obtain a second candidate indicator;

[0063] In this embodiment, in order to remove highly correlated features and avoid information redundancy or weight offset in subsequent weighted analysis, the redundancy discrimination threshold is set to 0.85. When the Pearson correlation coefficient of any two candidate indicators is greater than the redundancy discrimination threshold, they are considered redundant.

[0064] After finding all pairs of indicators with values ​​greater than the redundancy threshold, a redundant pair set is constructed. For each redundant pair in the set, the average correlation coefficient of each candidate feature indicator is calculated. Indicators with lower correlations are prioritized. If multiple indicators are redundant and have no clear advantage or disadvantage, a second candidate indicator can be selected based on information entropy, variation, domain knowledge, or stability in subsequent analysis.

[0065] Step S24: Calculate the comprehensive score of each candidate characteristic indicator in the second candidate indicators based on the subjective and objective weighted fusion method, sort the second candidate indicators based on the comprehensive score, and select a preset number of candidate characteristic indicators in the second candidate indicators as monitoring indicators.

[0066] In this example, the ability of different indicators to reflect the deformation and stress evolution of soft soil around piles is influenced by both the data variation characteristics (such as information entropy and volatility) and subjective knowledge such as engineering experience, expert judgment, and physical significance. For example, the vertical settlement rate of soil is usually a direct indicator of soft soil deformation and has a higher engineering experience weight, while the pore pressure fluctuation frequency may be important in some areas but not significant in others.

[0067] Therefore, a single objective or subjective weighting method is biased. To achieve a scientific assessment of the importance of indicators, a fusion mechanism of subjective and objective weighting is introduced, namely the entropy weight method (objective) + the AHP method (subjective). This method strikes a balance between data-driven and knowledge-driven approaches, improves the credibility and engineering adaptability of the final screening indicators, and obtains the final selected monitoring indicators.

[0068] In this step, the objective weight of each candidate feature indicator in the second candidate indicator is first calculated based on the entropy weight method. Specifically, the information entropy of each candidate feature indicator is calculated, and then the objective weight of each candidate feature indicator is calculated based on the information entropy.

[0069] Then, the subjective weight of each candidate characteristic indicator in the second candidate indicator is calculated based on the AHP method. Specifically, an indicator pair comparison matrix is ​​constructed by experts or technicians based on their experience. Each element in the indicator pair comparison matrix represents the relative importance between the two candidate characteristic indicators. The indicator pair comparison matrix is ​​then weighted using the eigenvector method to obtain the subjective weight matrix of the candidate characteristic indicators. Due to the subjectivity of human assignment, a consistency test is required to determine whether the subjective weight matrix is ​​reasonable. Therefore, the consistency ratio of the subjective weight matrix is ​​calculated and a consistency test is performed. If the consistency ratio is less than 0.1, the indicator pair comparison matrix needs to be adjusted and recalculated until the consistency test is met to obtain the final subjective weight matrix.

[0070] The subjective weight matrix is ​​used to obtain the subjective weight of each candidate characteristic indicator. The subjective weights and objective weights are then combined to determine the combined weight of each candidate characteristic indicator in the second candidate indicator. The combined weights are then used to calculate the comprehensive score for each candidate characteristic indicator in the second candidate indicator. The candidate characteristic indicators are ranked by comprehensive score, and in this step, the top six candidate characteristic indicators are selected as the final monitoring indicators.

[0071] Step S3: construct a model based on the monitoring data and monitoring indicators, and obtain the deformation-stress synergy map of the soft soil around the pile by considering risk assessment and spatial heterogeneity;

[0072] The step S3 comprises:

[0073] Step S31: constructing a mechanical response prediction model reflecting the deformation-stress coupling relationship of the soft soil around the pile based on the monitoring data;

[0074] It is understandable that traditional methods cannot explain why settlement continues to develop slowly after construction is completed, and why risk evolution is not discovered under complex working conditions. Therefore, this step uses a mechanical response prediction model to couple pore pressure, stress diffusion and time to explain the delayed settlement mechanism. At the same time, through model fitting, short-term and medium-term response prediction curves are provided, virtual disturbance scenarios are constructed, and potential risk areas are identified in advance.

[0075] In step S31, the steps of constructing the mechanical response prediction model are:

[0076] Step S311: constructing a basic mechanical response model based on the consolidation and seepage-mechanical coupling theory and the multi-field coupling mechanism, wherein the basic mechanical response model includes a pore pressure-settlement response model, a pile-soil contact interface strain function, a force-seepage-temperature coupling control equation group, and a stress evolution and settlement response function;

[0077] In this embodiment, the pore pressure-settlement response model is specifically:

[0078]

[0079] Where u represents the pore water pressure, c u represents the consolidation coefficient, represents the pore pressure diffusion capacity, represents the divergence operator, represents the pore pressure gradient, and t represents time.

[0080] The strain function of the pile-soil contact interface is specifically:

[0081] ∈ p-s (t)=f(Δu(t),Δσ h (t),T(t))

[0082] Where,∈ p-s (t) represents the pile-soil contact interface strain at time t, Δu(t) represents the change in pore water pressure at time t, and Δσ h (t) represents the horizontal stress change at time t, T(t) represents the soil temperature at time t, f(Δu(t), Δσ h (t), T(t)) represents the relationship between Δu(t), Δσ h (t) and T(t).

[0083] The force-seepage-temperature coupled control equations are simplified to two-dimensional plane strain, including the stress balance equation, constitutive relation and seepage control equation, which are:

[0084]

[0085] σ=D:(∈-∈ p -∈ T )

[0086]

[0087] Where, represents the divergence operator, σ represents the stress tensor, g represents the gravitational acceleration vector, ρ represents the soil density, D represents the constitutive stiffness matrix, ∈ represents the total strain tensor, ∈ prepresents plastic strain, ∈ T represents thermal expansion strain, k represents permeability coefficient, μ represents dynamic viscosity of liquid, ∈ v represents volumetric strain, and : represents double contraction.

[0088] The stress evolution and settlement response function is constructed based on the empirical model, specifically:

[0089] S(t)=S0+a·log(1+b·Δσ v (t))+c·u(t)

[0090] Where S(t) represents the soft soil settlement around the pile at time t, S0 represents the initial settlement value, a, b and c represent the fitting coefficients, Δσ v (t) represents the vertical stress increment at time t, and u(t) represents the pore water pressure at time t.

[0091] Step S312: Processing the monitoring data to obtain a structured monitoring data matrix;

[0092] Step S313: Fitting the basic mechanical response model based on the structured monitoring data matrix to obtain a mechanical prediction response model that reflects the deformation-stress coupling relationship of the soft soil around the pile.

[0093] Step S32: obtaining a predicted mechanical response value of each soil monitoring point at a future time through a mechanical response prediction model;

[0094] Step S33: Inputting the mechanical response prediction value and monitoring index into the risk assessment model to perform risk assessment, and obtaining the assessment results of each soil monitoring point in the soft soil around the pile, the assessment results including the risk score, status label and evolution trend;

[0095] It is understandable that a single monitoring indicator cannot comprehensively measure engineering risks, and there is a lack of a unified quantitative model to conduct comprehensive analysis and risk classification of monitoring indicators. Therefore, in this step, by constructing a multi-indicator driven risk assessment model, the complex and multi-dimensional monitoring information is mapped into an interpretable risk score, thereby realizing status identification, trend assessment, and subsequent risk classification and early warning triggering.

[0096] In step S33, the steps of constructing the risk assessment model are:

[0097] Step S331: constructing a risk factor vector using the mechanical response prediction value and the monitoring index, and setting each component in the risk factor vector as an input node of the Bayesian network;

[0098] In this embodiment, each monitoring indicator and each mechanical response prediction value (settlement prediction value, stress prediction value) is used as an input node of the Bayesian network to establish a complete risk input feature space. This allows the model to not only rely on observed data, but also integrate physical prediction information, thereby enhancing the modeling depth and generalization capabilities, and providing a clear and quantifiable input vector for Bayesian network reasoning.

[0099] Step S332: setting the risk score, status label, and evolution trend as the target node of the Bayesian network;

[0100] In this example, the risk score is a continuous variable (0-100) reflecting the overall risk level. The status label is a categorical variable representing normal, abnormal, or dangerous states. The evolution trend is a trend judgment variable, such as rising, stable, or declining. The evolution trend is the changing trend of the risk score, for example, whether the risk score is continuously rising, remaining stable, or gradually declining. Therefore, the multi-objective node format supports rich reasoning capabilities and helps meet multi-level engineering requirements (such as automatic early warning, manual intervention, and long-term trend prediction).

[0101] Step S333: setting a Bayesian network structure based on the causal relationship between the input node and the target node;

[0102] In this embodiment, the input node is used as the parent node, the output variable is used as the child node, and the Ye Si network structure is established through the guidance of expert knowledge.

[0103] Step S334: defining the prior distribution of the input nodes and the conditional probability table of the target node;

[0104] In this embodiment, the Bayesian network primarily uses discrete variables. The input and target nodes of the continuous variables must first be discretized, and then divided into different ranges based on their value ranges. For example, the risk score is discretized into 10-point ranges. The state labels then map the risk scores, for example, assigning the first three ranges as normal labels, the middle four ranges as abnormal labels, and the last three ranges as dangerous labels. The parent node contains the pore pressure change rate, and discretization is achieved by setting a threshold based on actual engineering experience to divide the corresponding intervals.

[0105] After discretization, the prior distribution of the input nodes is obtained based on historical data statistics. For target nodes with parent nodes, the probability distribution under each combination of parent nodes is defined. The conditional probability table of the target node is calculated based on the probability statistics of each state combination in the historical data.

[0106] Step S335: Train the Bayesian network using historical data, update the conditional probability table and adjust the Bayesian network structure to obtain a risk assessment model.

[0107] In this embodiment, the Bayesian network is trained using historical data (historical response values, historical monitoring indicators, actual assessed risk levels, status labels, trend evolution information, etc.), the conditional probability table is updated, and the Bayesian network structure is fine-tuned to obtain a risk assessment model.

[0108] Step S34: Using the evaluation results as node features and combining the spatial distribution relationship between soil monitoring points, a deformation-stress synergy map of the soft soil around the pile is constructed.

[0109] In this embodiment, in order to organically integrate the spatial distribution structure with the evaluation results, graph neural network modeling, temporal reasoning and spatial collaborative analysis are performed to obtain the deformation-stress collaborative map of the soft soil around the pile.

[0110] In step S34, constructing a deformation-stress synergistic map of the soft soil around the pile includes:

[0111] Step S341: defining each soil monitoring point as a graph node, and using the evaluation result of each soil monitoring point as the node feature of the corresponding graph node;

[0112] Step S342: defining edge connection relationships between graph nodes based on the spatial distribution relationship between soil monitoring points;

[0113] In this embodiment, since there is obvious spatial interlayer and directional correlation between the deformation and stress evolution of the soil (vertical settlement usually propagates between the upper and lower layers, and horizontal stress is transmitted radially or circumferentially), the engineering structure logical connection is used to construct the edge connection relationship between the graph nodes.

[0114] Specifically, the three-dimensional coordinates of each soil monitoring point are obtained. If the horizontal position distance between two soil monitoring points is within a small threshold (the horizontal and vertical coordinates are basically the same), the vertical distance is the layer thickness, which is set as a vertical edge to simulate the mechanical transmission and response coupling between the upper and lower soil layers.

[0115] If two soil monitoring points are located at the same depth (the difference between the vertical coordinates is less than the preset depth threshold) and the same radius (the horizontal distance from the pile center is less than the half-price preset threshold), and they are angularly distributed around the pile, they are connected and a circumferential edge is set to simulate the coordinated evolution of stress and settlement in different directions in the same layer of soil.

[0116] At the same time, when two soil monitoring points are located at the same depth and the same angle, the soil monitoring points at the same angle and different radii are connected to obtain radial edges, forming a path from the center of the pile to the outside, simulating the process of the pile transmitting mechanical influence to the surrounding soil, and capturing the deformation and stress evolution law of the pile load propagating radially through the soil.

[0117] Through the connection between upper and lower layers, the connection between the same layer and the near and far field connection between the pile and soil, the final adjacency relationship matrix, that is, the edge connection relationship between the graph nodes, is obtained.

[0118] Step S343: constructing a deformation-stress synergy graph of the soft soil around the pile based on the graph nodes, node features and edge connection relationships.

[0119] Step S4: Based on the deformation-stress collaborative map, the soft soil around the pile is identified as abnormal, the abnormal area is obtained through embedding learning and cluster analysis, and a graded warning is performed according to the abnormal area to obtain the warning result of the soft soil around the pile.

[0120] In step S4, obtaining the early warning result of soft soil around the pile includes:

[0121] Step S41: Embedding learning is performed on the deformation-stress collaborative graph based on the graph neural network to obtain a low-dimensional embedding representation of each graph node;

[0122] In this embodiment, a graph neural network is designed and trained (a GCN network is used in this step). Through a multi-layer message passing mechanism, neighbor node information is aggregated and a low-dimensional embedding representation of the nodes is learned. The low-dimensional embedding representation captures the complex spatial associations and feature coupling information between graph nodes and is mapped to a semantically rich feature space.

[0123] Step S42: Calculate the Euclidean distance between each graph node based on the low-dimensional embedding representation, and calculate the abnormality of each graph node through the Euclidean distance;

[0124] In this embodiment, when obtaining the neighboring nodes of each graph node, the number of neighboring nodes is dynamically adjusted. The number of neighboring nodes is increased in node-sparse areas (such as far-field soil) to avoid mean fluctuations caused by too few neighbors; the number of neighboring nodes is reduced in node-dense areas (such as areas near piles), focusing on core-related nodes, and automatically dividing the areas through density clustering algorithms (such as DBSCAN algorithm), and allocating adaptive numbers of neighboring nodes to different areas.

[0125] For each graph node, the Euclidean distance between its low-dimensional embeddings and its neighboring nodes is calculated to generate a node-neighboring node distance matrix. Based on this node-neighboring node distance matrix, the average of all Euclidean distances for each graph node is used to represent the node's outlier. Because this method essentially calculates the average degree of dissimilarity within each graph node's local neighborhood, a larger average Euclidean distance indicates a more outlier node.

[0126] Step S43: performing cluster analysis based on the abnormality degree to divide the potential abnormal areas in the soft soil around the pile;

[0127] In this embodiment, when setting anomaly thresholds based on historical data, a moving average method is used to adapt to temporal changes in soil conditions. For example, the anomaly threshold is calculated using the mean value within a preset time period and an adjustment parameter. Each graph node is marked according to its anomaly degree; if it exceeds the anomaly threshold, it is considered an anomaly node.

[0128] In order to organize discrete abnormal nodes into continuous spatial regions and facilitate engineering identification and location of abnormal regions, a clustering algorithm is used to group abnormal nodes and identify spatially adjacent node clusters with high abnormality. These node clusters are defined as abnormal regions.

[0129] Step S44: Calculate the outlier value of the abnormal area by the outlier degree of all graph nodes in the abnormal area;

[0130] In this embodiment, the outlier degree of all nodes within each outlier region is statistically calculated (averaged) to obtain the outlier value for that region. This numerically quantifies the overall risk level of the outlier region, facilitating hierarchical determination while minimizing the noise impact of single-point outliers.

[0131] Step S45: Compare the abnormal value with the preset graded warning standard to obtain the warning result of soft soil around the pile.

[0132] In this embodiment, graded warning thresholds (normal, slight warning, moderate warning, and severe warning) corresponding to abnormal values ​​are set, and the abnormal values ​​of the abnormal area are compared with the graded warning thresholds to determine its warning level, and the overall warning result of the soft soil around the pile is output, including the location of the abnormal area and the corresponding warning level.

[0133] In summary, the present invention constructs monitoring indicators that reflect the deformation and stress evolution of soft soil around piles through the preprocessing and feature extraction of multi-source monitoring data, and realizes the accurate quantification and dynamic tracking of the soil state around the pile. A screening strategy that combines subjective and objective weighting is adopted to eliminate redundant features, effectively improving the representativeness and stability of the indicators and ensuring the scientificity and reliability of subsequent analysis. At the same time, based on the fusion of mechanical response prediction and monitoring data, a complete risk factor input space is constructed, which enhances the depth and generalization ability of the model and lays a solid foundation for subsequent risk assessment.

[0134] Furthermore, the graph construction method, combined with the engineering structure logic, accurately depicts the spatial correlations between soil monitoring points. Using graph neural networks for low-dimensional embedding learning, the co-evolution characteristics of soil deformation and stress are fully captured. Cluster analysis based on node anomaly degree enables spatial identification and graded early warning of abnormal areas, providing a scientific, accurate, and real-time risk warning method for monitoring the soft soil condition around piles. This method not only improves the accuracy of anomaly identification but also enhances the interpretability of early warning results, promising prospects for widespread application in engineering projects.

[0135] Example 2:

[0136] like Figure 3 As shown, this embodiment provides a collaborative early warning system for soft soil deformation and stress around piles, the system comprising:

[0137] An acquisition unit 901 is configured to acquire monitoring data of soft soil around a pile based on monitoring points, wherein the monitoring data includes pile deformation data, pile stress data, soil deformation data, soil stress data, and environmental data. The monitoring points include pile monitoring points and soil monitoring points.

[0138] The feature extraction unit 902 is used to extract features from the monitoring data and obtain monitoring indicators reflecting the deformation and stress evolution of the soft soil around the pile based on information contribution differences and sensitivity selection;

[0139] A construction unit 903 is used to construct a model based on the monitoring data and monitoring indicators, and obtain a deformation-stress synergy map of the soft soil around the pile by considering risk assessment and spatial heterogeneity;

[0140] The early warning unit 904 is used to identify abnormalities in the soft soil around the pile based on the deformation-stress collaborative map, obtain abnormal areas through embedding learning and cluster analysis, and perform graded early warnings based on the abnormal areas to obtain early warning results for the soft soil around the pile.

[0141] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0142] Example 3:

[0143] Corresponding to the above method embodiment, this embodiment also provides a collaborative early warning device for soft soil deformation stress around piles. The collaborative early warning device for soft soil deformation stress around piles described below and the collaborative early warning method for soft soil deformation stress around piles described above can be referenced to each other.

[0144] Figure 4 FIG. 8 is a block diagram of a pile surrounding soft soil deformation stress coordinated early warning device 800 according to an exemplary embodiment. Figure 4 As shown, the pile surrounding soft soil deformation stress collaborative early warning device 800 may include: a processor 801, a memory 802. The pile surrounding soft soil deformation stress collaborative early warning device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0145] The processor 801 is used to control the overall operation of the pile-surrounding soft soil deformation stress collaborative early warning device 800 to complete all or part of the steps in the above-mentioned pile-surrounding soft soil deformation stress collaborative early warning method. The memory 802 is used to store various types of data to support the operation of the pile-surrounding soft soil deformation stress collaborative early warning device 800. Such data may include, for example, instructions for any application or method operating on the pile-surrounding soft soil deformation stress collaborative early warning device 800, as well as application-related data, such as contact information, sent and received messages, pictures, audio, video, etc. The memory 802 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. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the pile-surrounding soft soil deformation stress collaborative early warning device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 may include: Wi-Fi module, Bluetooth module, NFC module.

[0146] In an exemplary embodiment, the collaborative early warning device 800 for soft soil deformation and stress around piles can 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 to execute the above-mentioned collaborative early warning method for soft soil deformation and stress around piles.

[0147] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When executed by a processor, the program instructions implement the steps of the aforementioned method for collaboratively warning soft soil deformation and stress around piles. For example, the computer-readable storage medium may be the aforementioned memory 802 including the program instructions. The program instructions may be executed by the processor 801 of the device 800 for collaboratively warning soft soil deformation and stress around piles to implement the aforementioned method for collaboratively warning soft soil deformation and stress around piles.

[0148] Example 4:

[0149] Corresponding to the above method embodiment, this embodiment further provides a readable storage medium. The readable storage medium described below and the above-described method for coordinated early warning of soft soil deformation stress around a pile can refer to each other.

[0150] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the collaborative early warning method for soft soil deformation stress around piles of the above method embodiment.

[0151] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0152] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0153] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A collaborative early warning method for soft soil deformation stress around piles, characterized in that: include: Acquiring monitoring data of soft soil around the pile based on monitoring points, the monitoring data including pile deformation data, pile stress data, soil deformation data, soil stress data and environmental data, the monitoring points including pile monitoring points and soil monitoring points; Feature extraction is performed on the monitoring data. Based on the difference in information contribution and sensitivity selection, monitoring indicators reflecting the deformation and stress evolution of the soft soil around the pile are obtained. Based on the monitoring data and monitoring indicators, a model is constructed, and by considering risk assessment and spatial heterogeneity, a deformation-stress synergy map of the soft soil around the pile is obtained; Abnormal identification of soft soil around piles is performed based on the deformation-stress collaborative map. Abnormal areas are obtained through embedding learning and cluster analysis. Graded warnings are performed based on the abnormal areas to obtain the early warning results of soft soil around piles.

2. The method for coordinated early warning of soft soil deformation and stress around piles according to claim 1 is characterized in that ,The steps for obtaining the monitoring indicators are: Constructing a first candidate indicator through monitoring data, wherein the first candidate indicator includes a plurality of candidate feature indicators; Calculate the Pearson correlation coefficient matrix between multiple candidate feature indicators through the first candidate indicator to obtain the Pearson correlation coefficient between every two candidate feature indicators; The Pearson correlation coefficient is used to eliminate the redundancy of multiple candidate feature indicators to obtain the second candidate indicator; The comprehensive score of each candidate characteristic indicator in the second candidate indicators is calculated based on the subjective and objective weighted fusion method. After the second candidate indicators are ranked based on the comprehensive score, a preset number of candidate characteristic indicators in the second candidate indicators are selected as monitoring indicators.

3. The method for coordinated early warning of soft soil deformation and stress around piles according to claim 1 is characterized in that The model is constructed based on monitoring data and monitoring indicators. By considering risk assessment and spatial heterogeneity, the deformation-stress synergy map of the soft soil around the pile is obtained, including: Based on the monitoring data, a mechanical response prediction model reflecting the deformation-stress coupling relationship of the soft soil around the pile is constructed; Obtain the predicted mechanical response value of each soil monitoring point at a future moment through the mechanical response prediction model; Inputting the predicted mechanical response value and monitoring index into the risk assessment model for risk assessment, obtaining the assessment results of each soil monitoring point in the soft soil around the pile, the assessment results including risk score, status label and evolution trend; Taking the evaluation results as node features and combining the spatial distribution relationship between soil monitoring points, a deformation-stress synergy map of the soft soil around the pile is constructed.

4. The method for coordinated early warning of soft soil deformation stress around piles according to claim 3 is characterized in that ,The steps of constructing the mechanical response prediction model are: A basic mechanical response model is constructed based on the consolidation and seepage-mechanical coupling theory and the multi-field coupling mechanism. The basic mechanical response model includes a pore pressure-settlement response model, a pile-soil contact interface strain function, a force-seepage-temperature coupling control equation group, and a stress evolution and settlement response function. Process the monitoring data to obtain a structured monitoring data matrix; The basic mechanical response model is fitted based on the structured monitoring data matrix, and a mechanical prediction response model reflecting the deformation-stress coupling relationship of the soft soil around the pile is obtained.

5. The method for coordinated early warning of soft soil deformation and stress around piles according to claim 3 is characterized in that ,The steps of constructing the risk assessment model are: A risk factor vector is constructed through mechanical response prediction values ​​and monitoring indicators, and each component in the risk factor vector is set as an input node of the Bayesian network; Set the risk score, status label and evolution trend as the target nodes of the Bayesian network; Setting up the Bayesian network structure based on the causal relationship between input nodes and target nodes; Define the prior distribution of input nodes and the conditional probability table of target nodes; The Bayesian network is trained through historical data, the conditional probability table is updated and the Bayesian network structure is adjusted to obtain a risk assessment model.

6. The method for coordinated early warning of soft soil deformation and stress around piles according to claim 3 is characterized in that The construction of the deformation-stress synergistic map of the soft soil around the pile includes: Each soil monitoring point is defined as a graph node, and the evaluation result of each soil monitoring point is used as the node feature of the corresponding graph node; Define the edge connection relationship between graph nodes according to the spatial distribution relationship between soil monitoring points; The deformation-stress synergistic graph of soft soil around piles is constructed based on graph nodes, node features and edge connection relationships.

7. The method for coordinated early warning of soft soil deformation and stress around piles according to claim 1 is characterized in that The early warning result of the soft soil around the pile includes: Embedding learning of the deformation-stress collaborative graph is performed based on a graph neural network to obtain a low-dimensional embedding representation of each graph node; Calculate the Euclidean distance between each graph node based on the low-dimensional embedding representation, and calculate the abnormality of each graph node through the Euclidean distance; Cluster analysis is performed through anomaly degree to divide potential abnormal areas in the soft soil around the pile; The outlier value of the abnormal area is calculated by the outlier degree of all graph nodes in the abnormal area; The abnormal values ​​are compared with the preset graded warning standards to obtain the warning results of soft soil around the pile.

8. A coordinated early warning system for soft soil deformation and stress around piles, characterized in that: include: an acquisition unit, configured to acquire monitoring data of the soft soil around the pile based on monitoring points, the monitoring data including pile deformation data, pile stress data, soil deformation data, soil stress data, and environmental data, the monitoring points including pile monitoring points and soil monitoring points; The feature extraction unit is used to extract features from the monitoring data and obtain monitoring indicators reflecting the deformation and stress evolution of the soft soil around the pile based on the difference in information contribution and sensitivity selection; The construction unit is used to construct a model based on monitoring data and monitoring indicators, and obtain the deformation-stress synergy map of the soft soil around the pile by considering risk assessment and spatial heterogeneity; The early warning unit is used to identify abnormalities in soft soil around piles based on the deformation-stress collaborative map. The abnormal areas are obtained through embedding learning and cluster analysis, and graded early warnings are performed based on the abnormal areas to obtain early warning results for soft soil around piles.

9. A collaborative early warning device for soft soil deformation and stress around piles, characterized in that: include: memory for storing computer programs; A processor is configured to implement the steps of the method for collaborative early warning of soft soil deformation and stress around piles as claimed in any one of claims 1 to 8 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the collaborative early warning method for deformation and stress of soft soil around a pile as claimed in any one of claims 1 to 7.

Images