Basement anti-floating pile stress monitoring method and system

Abstract

The invention provides a basement anti-floating pile stress monitoring method and system, and relates to the technical field of anti-floating pile monitoring, and the method comprises the steps: collecting a plurality of stress monitoring data sets corresponding to a plurality of service moments; collecting an underground water level change data sequence of an area where the anti-floating pile structure is located; in combination with the groundwater level change data sequence and the plurality of stress monitoring data sets, carrying out equidirectivity verification on the evolution trend; generating a predicted settlement risk index; and when the predicted settlement risk index is greater than a preset probability threshold, generating an alarm signal. The technical problem that in the prior art, due to dependence on static data collection and lack of deep analysis on the stress change trend, the optimal intervention opportunity is missed can be solved, the stress state of the pile body can be analyzed in real time, the settlement risk can be accurately judged, early warning is automatically triggered when the risk exceeds the preset threshold value, and the risk is effectively prevented from being damaged. The technical effects of improving the safety of underground engineering and preventing the failure risk in advance are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of anti-floating pile monitoring, and in particular to a method and system for monitoring stress of anti-floating piles in basements. Background Art

[0002] With the rapid development of urban construction and underground engineering, basement anti-floating piles, as an important infrastructure, are widely used to ensure the anti-floating and stability of underground buildings. Under the influence of external loads and groundwater pressure, anti-floating piles will produce certain stress and deformation. In some cases, anti-floating piles may fail due to overload, groundwater level changes or other environmental factors, leading to structural settlement, tilting or even catastrophic damage. Therefore, accurately assessing the stress state and settlement risk of anti-floating piles and early warning of possible failure problems have become the key to ensuring the safety of underground engineering.

[0003] In the existing technology, although a certain number of stress monitoring methods have been proposed, most traditional monitoring systems only rely on static data collection and lack in-depth analysis of stress change trends, thus missing the best time for intervention. Summary of the invention

[0004] The purpose of this application is to provide a basement anti-floating pile stress monitoring method and system to solve the technical problem in the prior art of missing the best intervention opportunity due to reliance on static data collection and lack of in-depth analysis of stress change trends.

[0005] In view of the above problems, the present application provides a method and system for monitoring the stress of anti-floating piles in a basement.

[0006] In the first aspect, the present application provides a method for monitoring stress of anti-floating piles in a basement, which is implemented by a basement anti-floating pile stress monitoring system, wherein the method for monitoring stress of anti-floating piles in a basement includes: determining a sensor network for stress detection on the anti-floating pile structure of the basement to be monitored, and collecting multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure; based on the multiple service moments, collecting a groundwater level change data sequence in the area where the anti-floating pile structure is located; combining the groundwater level change data sequence and the multiple stress monitoring data sets to perform isotropic verification of the evolution trend; if the isotropic verification passes, predicting the settlement risk of the basement floor based on the multiple stress monitoring data sets, and generating a predicted settlement risk index; when the predicted settlement risk index is greater than a preset probability threshold, generating an alarm signal.

[0007] In the second aspect, the present application also provides a basement anti-floating pile stress monitoring system for executing the basement anti-floating pile stress monitoring method as described in the first aspect, wherein the basement anti-floating pile stress monitoring system includes: a stress data collection module, used to determine the sensor network used for stress detection on the anti-floating pile structure of the basement to be monitored, and collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure; a groundwater level data acquisition module, used to collect a groundwater level change data sequence in the area where the anti-floating pile structure is located based on the multiple service moments; a isotropic verification module, used to perform isotropic verification of the evolution trend in combination with the groundwater level change data sequence and the multiple stress monitoring data sets; a settlement risk prediction module, used to predict the settlement risk of the basement floor based on the multiple stress monitoring data sets if the isotropic verification is passed, and generate a predicted settlement risk index; an alarm module, used to generate an alarm signal when the predicted settlement risk index is greater than a preset probability threshold.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Determine the sensor network used for stress detection on the anti-floating pile structure of the basement to be monitored, collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure; based on the multiple service moments, collect the groundwater level change data sequence in the area where the anti-floating pile structure is located; combine the groundwater level change data sequence and the multiple stress monitoring data sets to verify the isotropy of the evolution trend; if the isotropy verification passes, predict the settlement risk of the basement floor based on the multiple stress monitoring data sets, and generate a predicted settlement risk index; when the predicted settlement risk index is greater than the preset probability threshold, generate an alarm signal. By combining multiple sets of historical failure stress data with real-time monitoring data, and using a finite element model for failure analysis and risk assessment, dynamic monitoring and accurate prediction of anti-floating piles under complex environmental conditions are achieved, and the stress state of the pile body can be analyzed in real time, the settlement risk can be accurately judged, and an early warning can be automatically triggered when the risk exceeds the preset threshold, achieving the technical effect of improving the safety of underground projects and preventing failure risks in advance.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a flow chart of the basement anti-floating pile stress monitoring method applied in this application.

[0012] Figure 2 This is a schematic diagram of the structure of the basement anti-floating pile stress monitoring system for this application.

[0013] Explanation of the reference numerals: stress data collection module 11 , groundwater level data collection module 12 , isotropic verification module 13 , settlement risk prediction module 14 , alarm module 15 . DETAILED DESCRIPTION

[0014] This application solves the technical problem of missing the best intervention opportunity in the prior art by providing a stress monitoring method and system for basement anti-floating piles, which relies on static data collection and lacks in-depth analysis of stress change trends. By combining multiple sets of historical failure stress data with real-time monitoring data, and using finite element models for failure analysis and risk assessment, dynamic monitoring and accurate prediction of anti-floating piles under complex environmental conditions are achieved. It can analyze the stress state of the pile body in real time, accurately judge the risk of settlement, and automatically trigger an early warning when the risk exceeds the preset threshold, thereby achieving the technical effect of improving the safety of underground projects and preventing failure risks in advance.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] For example, please refer to the attached Figure 1 The present application provides a basement anti-floating pile stress monitoring method, wherein the basement anti-floating pile stress monitoring method is applied to a basement anti-floating pile stress monitoring system, and the basement anti-floating pile stress monitoring method specifically includes the following steps: Step 1: Determine a sensor network for stress detection on the anti-floating pile structure of the basement to be monitored, and collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure.

[0017] Specifically, anti-floating piles are usually used in basement construction to resist buoyancy and provide support. In order to ensure the comprehensiveness and accuracy of monitoring, the layout of the sensor network must fully consider the key positions of the anti-floating pile structure, especially the changes at different depths. This is because the stress state of the anti-floating pile usually shows different trends with different depths, and the stress response of the shallow and deep layers may be completely different. In the design of the sensor network, strain gauges are the most commonly used sensor type. Strain gauges can accurately measure material deformation caused by external loads or internal stresses. By recording deformation data, the stress changes of the structure can be indirectly inferred. Strain gauges will be installed at multiple depths of the anti-floating pile, such as the middle of the shallow layer, the bottom of the deep layer, and the middle layer, to ensure that the stress state of the anti-floating pile can be fully reflected.

[0018] Next, the sensor network collects multiple stress monitoring data sets corresponding to multiple service moments. Multiple service moments refer to multiple moments from the time the anti-floating piles are installed and put into use until now. The data collected by each strain gauge will be recorded as a stress monitoring data set, which will accumulate over time to form multiple stress monitoring data sets at multiple service moments at different depths. That is, one depth position corresponds to one stress monitoring data set, and each stress monitoring data set contains data collected at multiple service moments.

[0019] Step 2: Based on the multiple service moments, a data sequence of groundwater level changes in the area where the anti-floating pile structure is located is collected.

[0020] Specifically, when monitoring the stress state of the anti-floating pile structure in the basement, the change of groundwater level is an important external factor, because the fluctuation of groundwater level may directly affect the stress condition of the anti-floating pile and its overall stability. Therefore, in order to more comprehensively understand the stress state of the anti-floating pile at different service times, it is necessary to collect the groundwater level change data series in the area at the same time. The impact of groundwater level change can be combined with stress monitoring data to help analyze the behavior of the pile under different environmental conditions. The fluctuation of groundwater level is usually affected by factors such as seasonal changes, precipitation, and the dynamics of the surrounding groundwater system. Especially in areas with groundwater or tidal effects, the rise and fall of groundwater level may cause the buoyancy of the anti-floating pile to change, thereby having an important impact on the stress of the pile body. Collecting groundwater level change data usually requires the deployment of water level monitoring sensors. These sensors can be installed at multiple points around the basement or in the area where the anti-floating pile is located to form a network to achieve comprehensive monitoring of the groundwater level. Generally, pressure sensors, buoys or conductivity sensors are used to monitor the changes in water level in real time and generate groundwater level change data series.

[0021] Step 3: Combining the groundwater level change data series and the multiple stress monitoring data sets to verify the isotropicity of the evolution trend.

[0022] Specifically, when conducting stress monitoring of anti-floating piles, there is a certain correlation between the change in groundwater level and the stress state of the pile body. By verifying the equidirectionality of the evolution trend of the groundwater level change data sequence and multiple stress monitoring data sets, it is determined whether the two have synchronous or similar change trends, thereby inferring whether the monitored stress data is accurate, determining the accuracy of the strain gauge, and preventing inaccurate stress monitoring due to the inaccuracy of the strain gauge. For example, if the stress value shows a corresponding increasing trend when the groundwater level rises, or the stress decreases when the groundwater level drops, it means that the change trends of the two are equidirectional.

[0023] Step 4: If the isotropic verification is passed, the settlement risk of the basement floor is predicted based on the multiple stress monitoring data sets to generate a predicted settlement risk index.

[0024] Specifically, if the isotropic verification is passed, it means that the change in groundwater level is consistent with the stress fluctuation trend of the anti-floating piles, indicating that the monitored data can more accurately reflect the actual stress state. In this case, the settlement risk of the basement floor can be predicted based on multiple stress monitoring data sets. By considering the stress state of the pile body, especially under different water level changes and soil conditions, how the stress of the anti-floating piles affects the stability of the basement floor. Specifically, through numerical simulation methods such as finite element analysis, a mathematical model of the anti-floating piles and basement structure can be established to simulate its response under different load conditions. On this basis, the model can perform failure analysis on the stress of the pile body, determine the structural safety under different stress conditions, and thus predict the settlement risk, and generate a settlement risk index. This index reflects the possibility of basement floor settlement, can effectively evaluate the potential risk of floor settlement, and provide strong data support for the safety management of basement structures.

[0025] Step 5: When the predicted subsidence risk index is greater than a preset probability threshold, an alarm signal is generated.

[0026] Specifically, when the predicted settlement risk index is greater than the preset probability threshold, an alarm signal is automatically generated to remind relevant personnel to take emergency measures to prevent potential structural failure and settlement problems. The alarm signal can be in various forms, depending on the design requirements of the system and the actual application environment. For example, it may be through sound alarm, visual alarm (displaying warning signs or red warning information on the monitoring interface of the control center), SMS or email notification, etc. The role of this alarm mechanism is to warn of potential settlement risks in advance, avoid safety accidents or property losses caused by uncontrolled settlement, and ensure the stability of the basement structure.

[0027] Further, step three of this application includes: For the multiple depth positions, a stable relationship between stress changes at different depths is constructed; based on the groundwater level change data sequence, the stress change trend of the anti-floating pile is predicted to generate a predicted change trend; and whether the changes in the multiple stress monitoring data sets satisfy the stable relationship between stress changes and the predicted change trend is analyzed to complete the verification of the isotropic nature of the evolution trend.

[0028] Specifically, when constructing a stress monitoring system for anti-floating piles in basements, it is very important to ensure a stable relationship between stress changes at different depths. This is because the stress influencing factors of anti-floating piles at different depths are different, especially the change in groundwater level will have different degrees of impact on the pile body. By constructing a stable relationship between stress changes, it can help determine whether the stress between layers conforms to the expected pattern, laying the foundation for subsequent stress prediction and trend analysis. First, historical data analysis is performed on stress data at multiple depths, and stress monitoring data sets at different depths over a certain period of time are collected, including stress fluctuations at different depths of the pile body, such as the severity of the change. On this basis, through statistical analysis methods, such as variance analysis or regression analysis, a stable relationship between stress changes at different depths is constructed. The stable relationship means that the stress change patterns at different depths have consistent regularity, such as the change rate and change amplitude of the shallow layer are greater than those of the middle layer.

[0029] Further, based on the collected groundwater level change data sequence, the stress change trend of the anti-floating pile is predicted. Generally speaking, the rise of groundwater level will increase the buoyancy of the anti-floating pile, thereby exerting a certain tensile force on the pile body, causing the stress in the shallow and middle layers to increase. When the groundwater level drops, the buoyancy decreases, and the force on the pile body tends to stabilize or decrease. For this reason, a time series prediction model (such as the autoregressive integrated moving average model ARIMA) or a machine learning method (such as regression tree, support vector machine) can be used to analyze the groundwater level change data and generate the corresponding stress change prediction trend. For example, by collecting the groundwater level data and the corresponding stress data of the past few months, a stress change prediction model can be trained to predict the stress change trend in the future under a given groundwater level data sequence, and obtain the predicted change trend. Finally, the changes in multiple stress monitoring data sets are compared with the predicted change trends to check whether the stress change stability relationship and the predicted change trend are met. This aims to determine whether the actually collected stress data are consistent with the stress change trend caused by the groundwater level change. If the monitoring data is consistent with the predicted trend, the isotropic verification passes, otherwise it fails, thereby ensuring the accuracy of stress data collection and improving monitoring accuracy.

[0030] Furthermore, the present application also includes: Based on the multiple depth positions, a historical stress monitoring data set is collected; based on the historical stress monitoring data set, stress fluctuation indicators of the multiple depth positions are calculated; and the relative relationship between the stress fluctuation indicators of the multiple depth positions is analyzed to generate the stress change stability relationship.

[0031] Specifically, the steps to construct a stable relationship between stress changes at different depths include: first, historical data collection is required for multiple depth positions of the same anti-floating pile structure as the basement to be monitored, including stress information at different depths, such as historical stress monitoring data of shallow layers (such as 5 meters), middle layers (such as 10 meters) and deep layers (such as 20 meters). After the historical stress data collection is completed, the next step is to calculate the stress fluctuation index at each depth position. The stress fluctuation index is an important quantitative parameter reflecting the amplitude, frequency and stability of stress changes. Common stress fluctuation indicators include: standard deviation, fluctuation amplitude, frequency, etc. After calculating the stress fluctuation index at each depth position, the relative relationship between the stress fluctuation indicators at different depth positions is further compared. The analysis of this relative relationship is to understand how stress changes at different depths are related to each other. It is assumed that the stress fluctuation indicators at the shallow and middle layers are relatively close, and the change trends are basically the same, while the stress fluctuation amplitude of the deep layer is significantly smaller than that of the shallow and middle layers, so as to generate a stable relationship between stress changes. The stable relationship between stress changes can be regarded as a regular description of stress changes between different depth positions, providing support for subsequent isotropic verification, thereby ensuring monitoring accuracy.

[0032] Furthermore, the present application also includes: Taking the anti-floating pile structure and the corresponding regional soil type as constraints, a set of groundwater level change data samples and a set of corresponding anti-floating pile stress change trend samples are collected; a stress change prediction model is trained with the set of groundwater level change data samples and the set of anti-floating pile stress change trend samples; the groundwater level change data sequence is analyzed by the stress change prediction model to generate the predicted change trend.

[0033] Specifically, with the anti-floating pile structure and the corresponding regional soil type as constraints, a set of groundwater level change data samples and a set of corresponding anti-floating pile stress change trend samples of the same characteristics are collected. Specifically, they can be obtained through historical water level monitoring data and historical anti-floating pile stress monitoring data. The next step is to use these data to train the stress change prediction model. Usually, this process will use machine learning or regression analysis and other methods to build a model that can model the relationship between groundwater level change and anti-floating pile stress change as a stress change prediction model. Common training methods include: Multiple regression: Use the groundwater level change data sample set and the anti-floating pile stress change trend sample set as independent variables and dependent variables, and perform regression analysis to establish a mathematical relationship between the two. Support vector machine (SVM) regression: For nonlinear relationships, the support vector machine regression method can effectively fit the complex change pattern between groundwater level and stress. Neural network: Using deep learning methods, especially when the amount of data is large, a deep neural network model can be trained to learn the nonlinear relationship between groundwater level and stress through multi-level abstraction.

[0034] The stress change prediction model obtained through training can analyze the previously collected groundwater level change data series to generate the corresponding stress change trend, that is, the predicted change trend. In this way, the model can accurately generate future stress change trends based on the input groundwater level change data, which is crucial for the long-term stability assessment of anti-floating piles and can provide real-time data support for stress monitoring.

[0035] Furthermore, the present application also includes: Perform fluctuation trend analysis on the multiple stress monitoring data sets respectively to generate multiple fluctuation trends; determine whether the multiple fluctuation trends satisfy the stress change stability relationship and the predicted change trend; if so, the isotropic verification is passed, otherwise it is not passed.

[0036] Specifically, for the multiple stress monitoring data sets collected at multiple depths, fluctuation trend analysis is performed one by one to extract key features of the data that reflect the law of stress change, such as fluctuation amplitude, periodicity and change direction. Specifically, multiple stress monitoring data sets can be treated as time series, and smoothed (such as moving average) to extract the overall trend and analyze the fluctuation characteristics at the same time; the fast Fourier transform (FFT) is used to identify the main frequency components of periodic fluctuations, which is particularly suitable for detecting long-term fluctuation trends of stress; the mean, standard deviation and maximum amplitude of the fluctuation are calculated to quantify the fluctuation characteristics of stress, thereby obtaining multiple fluctuation trends. After completing the fluctuation trend analysis, it is necessary to compare the generated multiple fluctuation trends with the previously established stable relationship of stress change. The stable relationship of stress change describes the stress fluctuation law at different depths, and judge whether the fluctuation trend at each depth is consistent with the change direction in the stable relationship of stress change. For example, when the groundwater level rises, the stress in the shallow and middle layers should increase synchronously, while the change in the deep layer is relatively small. After comparing with the stable relationship, it is also necessary to compare the fluctuation trend with the predicted change trend generated by the groundwater level change prediction model. The predicted change trend is generated based on the historical laws of groundwater level fluctuations and stress changes, and reflects the expected pattern of the impact of groundwater level fluctuations on stress. Specifically, it is necessary to judge whether the change direction of the fluctuation trend is consistent with the predicted trend and whether the change direction is consistent. For example, when the groundwater level rises, the predicted stress increases. If the actual fluctuation trend shows a decrease in stress, there may be a situation where the isotropic verification fails.

[0037] Through the above two-step comparison, it is finally determined whether the fluctuation trend meets the stress change stability relationship and the predicted change trend. If it does, it is considered that the isotropic verification has passed, which indicates that the fluctuation of the groundwater level is consistent with the stress change of the anti-floating pile, and the monitoring and prediction results are credible. If it does not meet, the isotropic verification fails, thereby ensuring the reliability of monitoring.

[0038] Further, step 4 of this application includes: Finite element modeling is performed on the anti-floating pile structure to generate an anti-floating pile test model; an anti-floating pile failure test is performed based on the anti-floating pile test model to establish a failure stress condition; the multiple stress monitoring data sets are compared with the failure stress condition in terms of degree of difference to generate the predicted settlement risk index, wherein the predicted settlement risk index is inversely proportional to the degree of difference.

[0039] Specifically, the finite element modeling of the anti-floating pile structure provides the necessary theoretical support for evaluating the stress state and failure risk of the pile under various load conditions. By establishing a mathematical model of the anti-floating pile, the performance of the pile under different external environments can be accurately simulated, thereby predicting its possible failure mode and its impact on the settlement of the basement floor. First, the finite element modeling of the anti-floating pile is carried out to generate an anti-floating pile test model. The finite element model is to discretize the physical properties, geometric shape and stress conditions of the pile and the surrounding soil, and divide the entire structure into multiple small units for analysis. In the modeling process, it is necessary to consider a variety of complex factors of the anti-floating pile, including the material properties of the pile, soil type, groundwater level changes, and surface loads. Through appropriate boundary conditions and load models, the stress state and deformation behavior of the anti-floating pile under different working conditions are simulated. Next, based on the generated anti-floating pile test model, an anti-floating pile failure test is carried out. The goal of the failure test is to determine the failure mode of the pile under different stress conditions and its corresponding stress threshold. For example, during the simulation process, the load on the pile is gradually increased until the stress of the pile reaches the ultimate bearing capacity of the material, which leads to the failure of the pile. In this process, the anti-floating pile test model can help identify the failure point of the anti-floating pile and the stress value at the time of failure, and use these stress values ​​as failure stress conditions. The failure stress conditions usually include multiple key parameters, such as the maximum bearing stress of the pile, the damage location, and the failure form.

[0040] Once the failure stress condition is established, the monitored multiple stress monitoring data sets can be compared with the failure condition to evaluate the stress state of the current anti-floating pile. By analyzing multiple stress monitoring data sets, the stress changes at each depth can be extracted and compared with the failure stress condition. The degree of difference is generally calculated by calculating the relative difference between the actual stress and the failure stress condition. For example, the difference between the two is quantified using statistics such as relative error, absolute value of difference or standard deviation. The comparison result of this degree of difference can generate a predicted settlement risk index, which reflects whether the current anti-floating pile is close to the failure state. Specifically, if the difference between the monitored stress data and the failure stress condition is small, it indicates that the stress of the pile body is close to the failure state and the settlement risk is high; conversely, if the difference is large, it means that the stress of the pile body is far below the failure threshold and the settlement risk is low. The risk index is inversely proportional to the degree of difference, that is, the smaller the difference, the larger the risk index, indicating a higher settlement risk; the larger the difference, the smaller the risk index, indicating a lower settlement risk. In this way, the real-time collected stress monitoring data can be constantly compared with the failure stress conditions, timely assessing the settlement risk of the basement floor, and triggering an early warning when the risk exceeds the preset threshold. For example, assuming that the difference between the stress value at a certain deep position and the failure stress condition is less than the set threshold, it means that the pile at this position is close to failure and the settlement risk is significantly increased; if this risk exceeds the safety threshold, an alarm can be issued in time, and reinforcement measures or structural adjustments can be taken to effectively prevent settlement or other structural failures. The key to this process is to accurately reflect the stress and failure behavior of the pile through the finite element model, combine the real-time stress monitoring data for difference comparison, and then generate accurate settlement risk prediction indicators to provide a basis for the structural safety of the basement.

[0041] Furthermore, the present application also includes: Acquire multiple sets of historical failure stress data; perform cross-variation processing based on the multiple sets of historical failure stress data to generate multiple sets of expanded stress data; load the multiple sets of expanded stress data into the anti-floating pile test model to obtain target samples under the failure state; and establish the failure stress condition with the multiple sets of historical failure stress data and the target samples.

[0042] Specifically, multiple sets of historical failure stress data are obtained. These data usually come from monitoring records of similar anti-floating pile structures in past engineering projects, or are obtained through laboratory tests. Each set of historical data should include information such as stress values, load conditions, soil types, and groundwater level changes of the pile under different working conditions. These factors will affect the failure state of the pile. By integrating failure data from different piles, different construction stages, and different environmental conditions, we can fully understand the failure characteristics of anti-floating piles under various working conditions. Next, cross-variation processing is performed based on these multiple sets of historical failure stress data to generate multiple sets of expanded stress data. Cross-variation processing is a data enhancement method that is usually used to increase the diversity and coverage of data sets. Here, the purpose of cross-variation processing is to generate new virtual data samples by combining stress values, soil parameters, groundwater levels, and other factors in different historical data. For example, two sets of historical failure stress data can be cross-combined to create new stress data by combining their stress change trends or loading conditions. This processing method can make up for the possible deviations or deficiencies in the original data, making the model training more comprehensive and accurate.

[0043] The expanded stress data generated by cross-mutation processing is then loaded into the anti-floating pile test model. The anti-floating pile test model can simulate the stress and deformation behavior of the pile under different load conditions through finite element analysis or other numerical calculation methods. When loading multiple sets of expanded stress data, stress analysis will be performed based on these new data sets to simulate the specific performance of the pile under a failure state, including failure modes such as deformation, cracking or buckling when the pile is subjected to stress exceeding the limit value. In this way, the test model can obtain target samples under a failure state, which reflect the possible failure modes and stress thresholds of the pile under different conditions.

[0044] Finally, failure stress conditions are established using multiple sets of historical failure stress data and target samples obtained from the anti-floating pile test model. The failure stress conditions define the critical stress values ​​and deformation characteristics of the pile body that may fail under different working conditions. Through this series of steps, the final failure stress conditions not only reflect the failure stress thresholds under a variety of different working conditions, but also provide the necessary theoretical support for subsequent settlement risk prediction and safety assessment. Such failure stress conditions are an important basis for stability analysis and settlement risk prediction of anti-floating piles.

[0045] In summary, the basement anti-floating pile stress monitoring method provided by this application has the following technical effects: Determine the sensor network used for stress detection on the anti-floating pile structure of the basement to be monitored, collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure; based on the multiple service moments, collect the groundwater level change data sequence in the area where the anti-floating pile structure is located; combine the groundwater level change data sequence and the multiple stress monitoring data sets to verify the isotropy of the evolution trend; if the isotropy verification passes, predict the settlement risk of the basement floor based on the multiple stress monitoring data sets, and generate a predicted settlement risk index; when the predicted settlement risk index is greater than the preset probability threshold, generate an alarm signal. By combining multiple sets of historical failure stress data with real-time monitoring data, and using a finite element model for failure analysis and risk assessment, dynamic monitoring and accurate prediction of anti-floating piles under complex environmental conditions are achieved, and the stress state of the pile body can be analyzed in real time, the settlement risk can be accurately judged, and an early warning can be automatically triggered when the risk exceeds the preset threshold, achieving the technical effect of improving the safety of underground projects and preventing failure risks in advance.

[0046] Embodiment 2, based on the same inventive concept as the basement anti-floating pile stress monitoring method in the aforementioned embodiment 1, the present application also provides a basement anti-floating pile stress monitoring system, please refer to the attached Figure 2 , the basement anti-floating pile stress monitoring system comprises: The stress data collection module 11 is used to determine the sensor network used for stress detection on the anti-floating pile structure of the basement to be monitored, and collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure.

[0047] The groundwater level data collection module 12 is used to collect a groundwater level change data sequence in the area where the anti-floating pile structure is located based on the multiple service moments.

[0048] The isotropic verification module 13 is used to perform isotropic verification of the evolution trend by combining the groundwater level change data sequence and the multiple stress monitoring data sets.

[0049] The settlement risk prediction module 14 is used to predict the settlement risk of the basement floor based on the multiple stress monitoring data sets and generate a predicted settlement risk index if the isotropic verification is passed.

[0050] The alarm module 15 is used to generate an alarm signal when the predicted subsidence risk index is greater than a preset probability threshold.

[0051] Furthermore, the isotropic verification module 13 in the basement anti-floating pile stress monitoring system is also used for: For the multiple depth positions, a stable relationship between stress changes at different depths is constructed; based on the groundwater level change data sequence, the stress change trend of the anti-floating pile is predicted to generate a predicted change trend; and whether the changes in the multiple stress monitoring data sets satisfy the stable relationship between stress changes and the predicted change trend is analyzed to complete the verification of the isotropic nature of the evolution trend.

[0052] Furthermore, the isotropic verification module 13 in the basement anti-floating pile stress monitoring system is also used for: Based on the multiple depth positions, a historical stress monitoring data set is collected; based on the historical stress monitoring data set, stress fluctuation indicators of the multiple depth positions are calculated; and the relative relationship between the stress fluctuation indicators of the multiple depth positions is analyzed to generate the stress change stability relationship.

[0053] Furthermore, the isotropic verification module 13 in the basement anti-floating pile stress monitoring system is also used for: Taking the anti-floating pile structure and the corresponding regional soil type as constraints, a set of groundwater level change data samples and a set of corresponding anti-floating pile stress change trend samples are collected; a stress change prediction model is trained with the set of groundwater level change data samples and the set of anti-floating pile stress change trend samples; the groundwater level change data sequence is analyzed by the stress change prediction model to generate the predicted change trend.

[0054] Furthermore, the isotropic verification module 13 in the basement anti-floating pile stress monitoring system is also used for: Perform fluctuation trend analysis on the multiple stress monitoring data sets respectively to generate multiple fluctuation trends; determine whether the multiple fluctuation trends satisfy the stress change stability relationship and the predicted change trend; if so, the isotropic verification is passed, otherwise it is not passed.

[0055] Furthermore, the settlement risk prediction module 14 in the basement anti-floating pile stress monitoring system is also used for: Finite element modeling is performed on the anti-floating pile structure to generate an anti-floating pile test model; an anti-floating pile failure test is performed based on the anti-floating pile test model to establish a failure stress condition; the multiple stress monitoring data sets are compared with the failure stress condition in terms of degree of difference to generate the predicted settlement risk index, wherein the predicted settlement risk index is inversely proportional to the degree of difference.

[0056] Furthermore, the settlement risk prediction module 14 in the basement anti-floating pile stress monitoring system is also used for: Acquire multiple sets of historical failure stress data; perform cross-variation processing based on the multiple sets of historical failure stress data to generate multiple sets of expanded stress data; load the multiple sets of expanded stress data into the anti-floating pile test model to obtain target samples under the failure state; and establish the failure stress condition with the multiple sets of historical failure stress data and the target samples.

[0057] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The basement anti-floating pile stress monitoring method and specific examples in Example 1 are also applicable to the basement anti-floating pile stress monitoring system in this embodiment. Through the above detailed description of the basement anti-floating pile stress monitoring method, those skilled in the art can clearly understand the basement anti-floating pile stress monitoring system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0058] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring stress of anti-floating piles in a basement, characterized in that: include: Determine a sensor network for stress detection on the anti-floating pile structure of the basement to be monitored, and collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure; Based on the multiple service moments, collecting a sequence of groundwater level change data in the area where the anti-floating pile structure is located; Combining the groundwater level change data sequence with the multiple stress monitoring data sets to verify the isotropy of the evolution trend; If the isotropic verification is passed, performing settlement risk prediction of the basement floor based on the multiple stress monitoring data sets to generate a predicted settlement risk index; When the predicted subsidence risk index is greater than a preset probability threshold, an alarm signal is generated.

2. The basement anti-floating pile stress monitoring method according to claim 1, characterized in that: Combining the groundwater level change data sequence with the multiple stress monitoring data sets to verify the isotropy of the evolution trend includes: For the multiple depth positions, construct a stable relationship of stress changes between different depths; Predicting the stress change trend of the anti-floating piles based on the groundwater level change data sequence to generate a predicted change trend; Analyze whether the changes of the multiple stress monitoring data sets satisfy the stress change stability relationship and the predicted change trend, and complete the verification of the isotropy of the evolution trend.

3. The method for monitoring stress of anti-floating piles in a basement according to claim 2, characterized in that: For the multiple depth positions, a stable relationship of stress changes between different depths is constructed, including: Based on the plurality of depth locations, collecting a historical stress monitoring data set; Calculating stress fluctuation indicators at the plurality of depth locations based on the historical stress monitoring data set; The relative relationship between the stress fluctuation indicators at the multiple depth positions is analyzed to generate the stress change stability relationship.

4. The method for monitoring stress of anti-floating piles in a basement according to claim 2, characterized in that: Predicting the stress change trend of the anti-floating pile based on the groundwater level change data sequence to generate the predicted change trend includes: Taking the anti-floating pile structure and the corresponding regional soil type as constraints, collecting a set of groundwater level change data samples and a set of corresponding anti-floating pile stress change trend samples; Training a stress change prediction model with the groundwater level change data sample set and the anti-floating pile stress change trend sample set; The groundwater level change data sequence is analyzed by the stress change prediction model to generate the predicted change trend.

5. The method for monitoring stress of anti-floating piles in a basement according to claim 2, characterized in that: Analyzing whether the changes of the multiple stress monitoring data sets satisfy the stress change stability relationship and the predicted change trend, and completing the isotropic verification of the evolution trend, including: performing fluctuation trend analysis on the multiple stress monitoring data sets respectively to generate multiple fluctuation trends; Determining whether the multiple fluctuation trends satisfy the stress change stability relationship and the predicted change trend; If so, the isotropic verification is passed, otherwise it is not passed.

6. The basement anti-floating pile stress monitoring method according to claim 1, characterized in that: Based on the multiple stress monitoring data sets, the settlement risk of the basement floor is predicted to generate a predicted settlement risk index, including: Performing finite element modeling on the anti-floating pile structure to generate an anti-floating pile test model; Perform an anti-floating pile failure test based on the anti-floating pile test model to establish a failure stress condition; The plurality of stress monitoring data sets are compared with the failure stress condition in terms of degree of difference to generate the predicted settlement risk index, wherein the predicted settlement risk index is inversely proportional to the degree of difference.

7. The method for monitoring stress of anti-floating piles in a basement according to claim 6, characterized in that: Based on the anti-floating pile test model, an anti-floating pile failure test is performed to establish a failure stress condition, including: Obtain multiple sets of historical failure stress data; Performing cross-variation processing based on the multiple sets of historical failure stress data to generate multiple sets of expanded stress data; Loading the multiple sets of expanded stress data into the anti-floating pile test model to obtain target samples in a failure state; The failure stress condition is established using the multiple groups of historical failure stress data and the target sample.

8. Basement anti-floating pile stress monitoring system, characterized by: The steps for implementing the basement anti-floating pile stress monitoring method according to any one of claims 1 to 7, the basement anti-floating pile stress monitoring system comprises: A stress data collection module, used to determine a sensor network for stress detection on the anti-floating pile structure of the basement to be monitored, and collect multiple stress monitoring data sets corresponding to multiple service moments, wherein the sensor network includes strain gauges located at multiple depth positions of the anti-floating pile structure; A groundwater level data acquisition module, used for acquiring a groundwater level change data sequence in the area where the anti-floating pile structure is located based on the multiple service moments; A isotropic verification module, used to perform isotropic verification of the evolution trend by combining the groundwater level change data sequence and the multiple stress monitoring data sets; A settlement risk prediction module, for predicting the settlement risk of the basement floor based on the multiple stress monitoring data sets and generating a predicted settlement risk index if the isotropic verification is passed; The alarm module is used to generate an alarm signal when the predicted subsidence risk index is greater than a preset probability threshold.

Images