Foundation pit robustness analysis method and equipment

Through random field simulation and convolutional neural network proxy model, combined with the weight fusion calculation of standard deviation and covariance, the problem of unconsidered spatial variability of soil parameters in foundation pit robustness analysis is solved, and the analysis efficiency and results are improved. Reliability to ensure the safety of foundation pit projects.

CN118917207AActive Publication Date: 2024-11-08GUANGXI ROAD & BRIDGE GRP CONSTR ENG CO LTD +1

Patent Information

Application Number
CN202411094103.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-08
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

The spatial variability of soil parameters cannot be fully considered in the existing foundation pit robustness analysis, resulting in the unreliable results of the foundation pit stability analysis.

Method used

Random field simulation and convolutional neural network proxy model are used to generate distribution images of soil properties through random field simulation, train the proxy model to calculate the mean of design response, and perform weight fusion calculation through standard deviation and covariance to obtain the foundation pit A good indicator.

Benefits of technology

It significantly improves the accuracy and reliability of the analysis efficiency and results, and can more scientifically evaluate the robustness of the foundation pit, provide reliable decision-making basis for foundation pit design and construction, and ensure the safety and stability of the foundation pit project.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917207A_ABST
    Figure CN118917207A_ABST
Patent Text Reader

Abstract

The invention discloses the technical field of foundation pit design analysis, and particularly discloses a foundation pit robustness analysis method and equipment, which can fully reflect the randomness of soil attributes by taking a convolutional neural network proxy model capable of considering spatial variability as the basis of robustness evaluation, and improve the robustness of the foundation pit. According to the method, the design response value of the foundation pit can be predicted, the accurate and real design response value of the physical mechanics can be predicted, the accuracy and the reliability of an analysis result are further ensured, meanwhile, the relationship between the design response values is comprehensively considered through weight fusion calculation, a scientific evaluation means is provided for foundation pit robustness evaluation, effective technical support is provided for engineering practice, and the method is suitable for popularization and application. A reliable decision basis is provided for foundation pit design and construction, and the safety and stability of foundation pit engineering are further ensured from the design perspective.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of foundation pit design and analysis, and in particular to a foundation pit robustness analysis method and equipment. Background Art

[0002] The existing foundation pit design usually adopts the deterministic design method, which means obtaining the geometric parameter combination that meets the safety requirements of anti-uplift, anti-overturning and lateral deformation of the support structure based on the determined geotechnical mechanics parameters (mean assumption). Due to the influence of soil parameter variability, on the basis of deterministic design, the analysis and design of the foundation pit robustness should also be considered, that is, when the uncertainty factors change within a given range, it must be ensured that the stability of the foundation pit support system is not affected.

[0003] Due to the effects of load history conditions and physical and chemical processes, natural soil has spatial variability in parameters such as strength and modulus. In traditional foundation pit robustness analysis, the soil parameters (physical and mechanical property values) at different locations in the soil layer cannot be accurately determined, and the shear strength of the entire soil layer can only be represented by the local mean, thus lacking consideration of the impact of soil parameter variability on the analysis results. Summary of the invention

[0004] In order to solve the problem that the existing foundation pit robustness analysis does not take into account the spatial variability of soil parameters, resulting in the inability to fully utilize various soil parameters to obtain reliable results in the foundation pit stability analysis, the present invention provides a foundation pit robustness analysis method and equipment.

[0005] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a foundation pit robustness analysis method, the method comprising:

[0007] S1. After performing random field simulation on the soil property values ​​of the target foundation pit, the soil property values ​​are mapped into the numerical model to obtain a number of first foundation pit samples; the first foundation pit samples include a distribution image of the soil property values ​​and a mean and variance of the soil property values;

[0008] S2. Calculate the design response mean corresponding to each first foundation pit sample by using the numerical model, label the first foundation pit sample according to the design response mean, and generate a data set;

[0009] S3, training a proxy model according to the data set to obtain a trained proxy model;

[0010] S4, repeat S2 to S3 to obtain trained proxy models corresponding to multiple design response means;

[0011] S5, repeat S1 to obtain a number of second foundation pit samples and then input them into a plurality of trained proxy models to obtain a plurality of design response prediction means;

[0012] S6. Perform weighted fusion calculation based on the standard deviation and covariance of the predicted mean of each design response to obtain the robustness index of the target foundation pit.

[0013] According to a specific implementation, in the above analysis method, the random field simulation includes:

[0014] A random field is constructed based on random parameters of the soil property values ​​using the Monte Carlo sampling method; wherein the random parameters include the mean, variance, coefficient of variation, vertical fluctuation distance and horizontal fluctuation distance of the soil property values.

[0015] According to a specific implementation, in the above analysis method, the soil property values ​​are selected from any three property values ​​of the physical and mechanical properties of the soil of the target foundation pit.

[0016] According to a specific implementation, in the above analysis method, the distribution image of the soil attribute value is an RGB image generated by numerical model conversion, including:

[0017] The three soil property values ​​of each unit body in the mapped numerical model are converted into R channel values, G channel values ​​and B channel values ​​respectively;

[0018] Assign the R channel values, G channel values ​​and B channel values ​​of all units to the R channel, G channel and B channel respectively to generate an RGB image.

[0019] According to a specific implementation, in the above analysis method, the design response mean includes the mean of pile body stress, the mean of pile body displacement, the mean of pit bottom uplift and the mean of peripheral settlement.

[0020] According to a specific implementation, in the above analysis method, the calculation formula for the standard deviation of each design response prediction mean is:

[0021]

[0022] Among them, σ i is the standard deviation of the predicted mean of the ith design response, x ik is the predicted mean of the i-th design response corresponding to the k-th second foundation pit sample, is the predicted mean of the i-th design response, and M is the number of samples in the second foundation pit.

[0023] According to a specific implementation, in the above analysis method, the calculation formula for the covariance of each design response prediction mean is:

[0024]

[0025] Among them, Cov(X i ,X j ) is the covariance between the predicted mean of the ith design response and the predicted mean of the jth design response, x ik is the predicted mean of the i-th design response corresponding to the k-th first random field sample, x jk is the predicted mean value of the j-th design response corresponding to the k-th second foundation pit sample, is the predicted mean of the ith design response, is the predicted mean of the j-th design response, and M is the number of samples in the second foundation pit.

[0026] According to a specific implementation, in the above analysis method, weight fusion is performed according to the standard deviation and covariance of each design response prediction mean, including:

[0027] The weights are assigned based on the standard deviation of the predicted mean of each design response, calculated as:

[0028]

[0029] Among them, ω i is the fusion weight of the predicted mean of the i-th design response, σ i , σ j is the standard deviation of the predicted means of the i-th and j-th design responses, and n is the number of types of the predicted means of the design responses;

[0030] The fusion calculation is performed according to the weight of each design response prediction mean, and the calculation formula is:

[0031]

[0032] Among them, σ p is the robustness index of the target foundation pit, Cov(X i ,X j ) is the covariance between the predicted mean of the ith design response and the predicted mean of the jth design response.

[0033] According to a specific implementation, in the above analysis method, the proxy model adopts a convolutional neural network.

[0034] In a second aspect, the present invention provides an electronic device comprising at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a foundation pit robustness analysis method as described in any one of the above items.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] Based on the technical solution provided by the present invention, a convolutional neural network proxy model that can consider spatial variability is used as the basis for robustness evaluation. Based on random field simulation, the randomness of soil properties can be fully reflected, and then the accurate and true physical and mechanical design response mean can be predicted, thereby ensuring the validity of the analysis results. In addition, the present invention adds a proxy model to replace the traditional numerical simulation analysis to obtain the various design response means of the foundation pit, which significantly improves the analysis efficiency, and enables each foundation pit project to have an applicable proxy model, further improving the accuracy and reliability of the obtained design response prediction mean. At the same time, the present invention calculates each obtained design response prediction mean through weight fusion, comprehensively considers the relationship between the various design response means, provides a scientific evaluation method for foundation pit robustness evaluation, provides effective technical support for engineering practice, and provides a reliable decision-making basis for foundation pit design and construction, further ensuring the safety and stability of foundation pit projects from a design perspective. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of a foundation pit robustness analysis method provided by an embodiment of the present invention;

[0038] Figure 2 An exemplary flow chart of a foundation pit robustness analysis method provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a numerical model of a foundation pit provided by an embodiment of the present invention;

[0040] Figure 4 An RGB image of the foundation pit numerical model provided by an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of prediction of the proxy model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0043] The terms "including" and "having" and any variations thereof in the embodiments of the present invention, the claims, and the drawings are intended to cover non-exclusive inclusions, for example, including a series of steps or units. The methods, systems, products, or devices are not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or devices.

[0044] Please refer to Figure 1 , which shows a schematic flow chart of a foundation pit robustness analysis method provided by an embodiment of the present invention, the analysis method comprising:

[0045] S1. After random field simulation of the soil property values ​​of the target foundation pit, the values ​​are mapped into the numerical model to obtain a number of first foundation pit samples.

[0046] S2. Calculate the design response mean corresponding to each first foundation pit sample through the numerical model, label the first foundation pit samples according to the design response mean, and generate a data set.

[0047] S3. Train a proxy model according to the data set to obtain a trained proxy model.

[0048] S4. Repeat S2 to S3 to obtain trained proxy models corresponding to multiple design response means.

[0049] S5. Repeat S1 to obtain a number of second foundation pit samples and input them into multiple trained proxy models to obtain multiple design response prediction means.

[0050] S6. Perform weighted fusion calculation based on the standard deviation and covariance of the predicted mean of each design response to obtain the robustness index of the target foundation pit.

[0051] In the existing foundation pit robustness analysis, most of the methods used are numerical simulation analysis, and the most commonly used is FLAC software. Usually, for a 2000-unit foundation pit model, it takes about 3 minutes for FLAC to run the calculation of the design response mean once, and 10,000 calculations take a total of 500 hours. However, using the proxy model method, only FLAC3D software is required to perform 500 calculations at most to build a training data set for the proxy model, and then it takes 10 minutes to train the model, with a total time of about 25 hours, and the calculation efficiency can be improved by 16 times. In addition, previous proxy models are usually unable to take into account the variability indicators of soil parameters. Therefore, an embodiment of the present invention provides a foundation pit robustness analysis method that uses a proxy model for numerical simulation analysis, which uses random field simulation to introduce soil parameter variability into the analysis, and uses this to train the proxy model to obtain a proxy model for foundation pit robustness analysis that can consider the spatial variability of soil parameters.

[0052] Furthermore, the geometric features (shape), support structure settings, etc. of each foundation pit project are different, and it is often difficult for the proxy model to take these features into account. Therefore, the proxy model provided in the embodiment of the present invention only considers the variability of the rock and soil attribute values, thereby training a suitable proxy model based on each foundation pit project, further improving the accuracy and reliability of the obtained design response prediction mean.

[0053] The technical solution provided by the embodiment of the present invention is further introduced and illustrated by means of specific implementation methods below.

[0054] Specifically, as described in S1 above, the soil property values ​​of the target foundation pit are subjected to random field simulation and then mapped to the numerical model to obtain a number of first foundation pit samples.

[0055] In this step, the numerical model of the target foundation pit can be established through the design parameters such as the survey and design data of the target foundation pit. After the establishment, the random field simulation is performed based on the random parameters of the soil attribute values ​​using the Monte Carlo sampling method to construct a random field sample. Among them, the random parameters include the mean, variance, coefficient of variation, vertical fluctuation distance and horizontal fluctuation distance of the soil attribute values. Subsequently, the constructed random field sample is mapped to the numerical model, and the first foundation pit sample is obtained through the numerical model. The first foundation pit sample includes the distribution image of the soil attribute values ​​and the mean and variance of the soil attribute values.

[0056] It should be noted that, since the distribution image of the soil property values ​​adopts an RGB image generated by numerical model conversion, based on the three channels in the RGB image, correspondingly, in the analysis method provided in the embodiment of the present invention, the soil property values ​​select any three property values ​​of the physical and mechanical properties of the soil of the target foundation pit.

[0057] Furthermore, the three soil property values ​​of each unit body in the mapped numerical model are converted into R channel values, G channel values ​​and B channel values ​​respectively;

[0058] Assign the R channel values, G channel values ​​and B channel values ​​of all units to the R channel, G channel and B channel respectively to generate an RGB image.

[0059] Specifically, as described in S2 above, the design response mean corresponding to each first foundation pit sample is calculated through the numerical model, and the first foundation pit samples are labeled according to the design response mean to generate a data set.

[0060] This step mainly provides training samples for the training of the proxy model through numerical simulation analysis.

[0061] Further, as described in S3 above, a proxy model is trained according to the data set to obtain a trained proxy model.

[0062] Specifically, as described in S4 above, S2 to S3 are repeated to obtain trained proxy models corresponding to multiple design response means.

[0063] Normally, a proxy model can only obtain a corresponding design response mean. Therefore, in order to obtain multiple design response means and provide higher reliability for robustness analysis, the embodiment of the present invention uses training to obtain different proxy models and then obtain different design response means. The design response mean is a physical and mechanical response value based on soil properties, that is, the design response that needs to be used and considered in foundation pit design.

[0064] Furthermore, the proxy model adopts a convolutional neural network. In a possible implementation, the proxy model provided by the embodiment of the present invention includes an input layer, a convolutional layer, an attention layer, a pooling layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer, and the learning rate, the hyperparameters of the convolutional layer and the pooling layer of the proxy model are determined by Bayesian hyperparameter optimization.

[0065] Specifically, as described in S5 above, S1 is repeated to obtain a number of second foundation pit samples, which are then input into a plurality of trained proxy models to obtain a plurality of design response prediction means.

[0066] It can be understood that in the above S1 to S4, after the numerical simulation analysis is performed on the first foundation pit sample, training data is provided for the proxy model in order to obtain a trained proxy model, which can then take over the numerical simulation analysis, perform fast and accurate analysis, and obtain the mean of each design response. Since the convolutional neural network has a significantly high efficiency in data processing, the number of the second foundation pit samples can be much larger than the number of the first foundation pit samples. For example, 500 copies of the first foundation pit sample can be generated to provide training for the proxy model. The number of second foundation pit samples input into the trained proxy model can reach 10,000 or more, thereby obtaining a more accurate mean of the design response.

[0067] Specifically, as described in S6 above, a weighted fusion calculation is performed based on the standard deviation and covariance of the predicted mean of each design response to obtain the robustness index of the target foundation pit.

[0068] The embodiment of the present invention proposes a method for weighted fusion of the predicted mean values ​​of various design responses, so that the obtained robustness index can be more comprehensive and reliable.

[0069] Furthermore, the standard deviation of the predicted mean of each design response is calculated as:

[0070]

[0071] Among them, σ i is the standard deviation of the predicted mean of the ith design response, x ik is the predicted mean of the i-th design response corresponding to the k-th second foundation pit sample, is the predicted mean of the i-th design response, and M is the number of samples in the second foundation pit.

[0072] The covariance of the predicted mean for each design response is given by:

[0073]

[0074] Among them, Cov(X i ,X j ) is the covariance between the predicted mean of the ith design response and the predicted mean of the jth design response, x ik is the predicted mean of the i-th design response corresponding to the k-th first random field sample, x jk is the predicted mean value of the j-th design response corresponding to the k-th second foundation pit sample, is the predicted mean of the ith design response, is the predicted mean of the j-th design response, and M is the number of samples in the second foundation pit.

[0075] The weight fusion is performed according to the standard deviation and covariance of the predicted mean of each design response, including:

[0076] The weights are assigned based on the standard deviation of the predicted mean of each design response, calculated as:

[0077]

[0078] Among them, ω i is the fusion weight of the predicted mean of the i-th design response, σ, σ j is the standard deviation of the predicted means of the i-th and j-th design responses, and n is the number of types of the predicted means of the design responses;

[0079] The fusion calculation is performed according to the weight of each design response prediction mean, and the calculation formula is:

[0080]

[0081] Among them, σ p is the robustness index of the target foundation pit, Cov(X i ,X j ) is the covariance between the predicted mean of the ith design response and the predicted mean of the jth design response.

[0082] Based on the technical solution provided by the present invention, a convolutional neural network proxy model that can consider spatial variability is used as the basis for robustness evaluation. Based on random field simulation, the randomness of soil properties can be fully reflected, and then the accurate and true physical and mechanical design response mean can be predicted, thereby ensuring the validity of the analysis results. In addition, the present invention adds a proxy model to replace the traditional numerical simulation analysis to obtain the various design response means of the foundation pit, which significantly improves the analysis efficiency, and enables each foundation pit project to have an applicable proxy model, further improving the accuracy and reliability of the obtained design response prediction mean. At the same time, the present invention calculates each obtained design response prediction mean through weight fusion, comprehensively considers the relationship between the various design response means, provides a scientific evaluation method for foundation pit robustness evaluation, provides effective technical support for engineering practice, and provides a reliable decision-making basis for foundation pit design and construction, further ensuring the safety and stability of foundation pit projects from a design perspective.

[0083] The technical solution provided by the embodiment of the present invention is further introduced and explained below based on specific implementation methods.

[0084] Please refer to Figure 2 , which shows an exemplary flow chart of the foundation pit robustness analysis method provided for an embodiment of the present invention.

[0085] In a possible implementation, in order to make the description of the technical solution clear, in this embodiment, the three physical and mechanical properties of the soil, namely cohesion, friction angle and elastic modulus, are selected as the above-mentioned soil properties, and the three physical and mechanical response values, namely the mean displacement of the support structure, the mean uplift of the pit bottom soil and the mean settlement around the foundation pit, are selected as the above-mentioned design response mean and design response prediction mean.

[0086] Specifically, in the above-mentioned foundation pit robustness analysis method, a foundation pit numerical model is first established based on the survey and design data, and then the spatial variability of the cohesion, friction angle and elastic modulus of the soil is considered, and a random field sample is obtained by random field simulation, and mapped to the numerical model of the foundation pit to obtain the cohesion, friction angle and elastic modulus of each unit body. Due to the existence of randomness, the results of each random field simulation are different, so m groups of cohesion, friction angle and elastic modulus distribution data, that is, random field samples, can be generated by sampling.

[0087] Furthermore, the first foundation pit sample is obtained through the random field sample, and the first foundation pit sample includes a distribution image of soil attribute values ​​and the mean and variance of the soil attribute values. Specifically, the distribution image of the soil attribute values ​​is an RGB image generated by numerical model conversion. Considering that each unit body in the numerical model has corresponding three attribute values ​​(cohesion, friction angle and elastic modulus), the three attribute values ​​are used as the RGB values ​​of the numerical model image, and a color image is constructed for input. Simply put: if the cohesion, friction angle and elastic modulus values ​​of a grid unit in the numerical model are a, b, and c respectively, then the color of the grid unit is (R=a, B=b, G=c), and each cell in the foundation pit model has a corresponding RGB value. Based on this, a foundation pit model color image mapped with soil attribute values ​​is constructed. The specific steps for generating the corresponding foundation pit model color image in each first foundation pit sample are as follows:

[0088] (1) Normalization: First, the three attribute values ​​of cohesion, friction angle and elastic modulus need to be normalized so that their range is between 0 and 1. This can be achieved by dividing each attribute value by the maximum value of the attribute.

[0089] (2) Scaling to the range of 0-255: Multiply the normalized value by 255 and convert it to an integer from 0 to 255. This is because the RGB values ​​of the image need to be in this range.

[0090] (3) Generate image: The cohesion, friction angle and elastic modulus values ​​of each unit of the model are respectively mapped to RGB values, and these data are converted into image format.

[0091] Based on the mean and variance of the cohesion, friction angle and elastic modulus of each first foundation pit sample mentioned above, a total of 6 numerical features and 1 RGB image feature are used as the input of the CNN convolutional neural network.

[0092] Based on the above m groups of random field samples, numerical simulation analysis (annotation) is carried out through numerical software to obtain the mean displacement of the supporting structure, the mean uplift of the bottom soil, and the mean settlement around the foundation pit corresponding to each random field sample as the output of the proxy model. Based on this, three proxy model training data sets containing m samples can be constructed for the mean displacement of the supporting structure, the mean uplift of the bottom soil, and the mean settlement of the soil around the foundation pit. The construction process is shown in the following table:

[0093] Table 1 is a schematic diagram of the construction of the training data set.

[0094]

[0095] The structure of the proxy model is input layer, convolution layer, attention layer, pooling layer, convolution layer, pooling layer, fully connected layer, and output layer. The learning rate of the model, the size of the convolution layer and the pooling layer, and other hyperparameters are determined by Bayesian hyperparameter optimization. The training data set containing m samples is divided into a training set, a test set, and a validation set according to the ratio of 80%, 10%, and 10%. The model is trained using the training set. The model establishes the weights and parameters of CNN by learning the training set, so that it learns the mapping from the physical and mechanical parameter image of the foundation pit model to the numerical calculation response of the model; the model hyperparameters are adjusted using the validation set, and the best model is selected by evaluating the performance of different hyperparameters on the validation set; the model performance is evaluated using the test set to check its generalization ability on unknown data. Among them, the training set and the validation set participate in model training, and the test set only participates in model evaluation and does not participate in model training.

[0096] Based on the above method, three proxy models are constructed to predict the mean displacement of the supporting structure, the mean uplift of the pit bottom soil, and the mean settlement around the foundation pit.

[0097] The robustness calculation of the foundation pit is carried out by using the proxy model trained above in combination with Monte Carlo sampling. When analyzing the stability of the foundation pit, we should not only pay attention to the deformation of the support structure, but also cannot ignore the displacement and deformation of the soil, such as the uplift of the soil at the bottom of the foundation pit and the settlement of the surrounding soil. Therefore, when evaluating the robustness of the foundation pit, it is necessary to comprehensively consider the fluctuation of the response value. For this reason, the embodiment of the present invention constructs the fusion standard deviation of the physical and mechanical response of the foundation pit support structure and the soil as the robustness indicator of the foundation pit system.

[0098] In a possible implementation, according to the above steps of generating m random field samples, new M random field samples are regenerated by Monte Carlo, where M is much larger than m. The second foundation pit samples corresponding to the M random field samples are obtained by the above steps. The M second foundation pit samples are input into three proxy models of the predicted mean displacement of the supporting structure, the predicted mean uplift of the pit bottom soil, and the predicted mean settlement around the foundation pit, respectively, to obtain 3*M groups of data.

[0099] Finally, weighted fusion is performed based on the standard deviation and covariance of the predicted mean of each design response to obtain the robustness index of the target foundation pit.

[0100] Furthermore, the technical solution provided by the embodiment of the present invention is further described below in conjunction with specific implementation methods.

[0101] In a subway construction project in a certain city, a deep foundation pit needs to be excavated for the construction of a subway station. The foundation pit is located in the city center, surrounded by dense buildings, with a high groundwater level and complex geological conditions. In order to ensure the safety and stability of the foundation pit during construction, the influence of the spatial variability of soil parameters on the stability of the foundation pit must be considered. The technical solution provided by the embodiment of the present invention is used to quantitatively analyze the robustness of the current foundation pit design solution.

[0102] First, based on the geological survey and design data, a numerical model of the foundation pit is established, including the foundation pit size, support structure, etc. Please refer to Figure 3 , which shows a schematic diagram of a numerical model of a foundation pit provided by an embodiment of the present invention.

[0103] Random field simulation is used to simulate the spatial variability of the three physical and mechanical properties of cohesion, friction angle and elastic modulus in the foundation pit model. Through multiple simulations, 500 sets of cohesion, friction angle and elastic modulus distribution data, namely random field samples, are generated.

[0104] The random field samples are mapped to the numerical model of the foundation pit, and the distribution of soil physical and mechanical parameters in each sample is different. Then, through the training step of the proxy model, a color image of the foundation pit numerical model mapped with soil attribute values ​​is generated through the foundation pit numerical model, such as Figure 4 As shown, it is an RGB image of the foundation pit numerical model provided by an embodiment of the present invention. At the same time, the mean and variance of the cohesion, friction angle and elastic modulus of each sample are calculated. The RGB image and the mean and variance are constructed into a first foundation pit sample. Then, the FLAC3D numerical analysis software is used to perform numerical simulation analysis on each first foundation pit sample, and the mean displacement of the supporting structure, the mean uplift of the pit bottom soil and the mean settlement around the foundation pit corresponding to each first foundation pit sample are calculated, and the first foundation pit sample is labeled as the sample. In summary, a total of 500 labeled first foundation pit samples are generated, which are used as the data set for training of the proxy model. Among them, the RGB image, mean and variance are used as model input, and the sample label is used as model output.

[0105] Using the above data sets, three CNN convolutional neural network proxy models were trained to predict the mean of design response predictions such as the displacement of the foundation pit support structure, the uplift of the pit bottom soil, and the settlement around the foundation pit. Figure 5 , which shows a prediction schematic diagram of the agent model provided by an embodiment of the present invention.

[0106] The hyperparameters of the three models after Bayesian hyperparameter optimization are shown in the following table:

[0107] Table 2 is a schematic diagram of the hyperparameters of the proxy model of the embodiment of the present invention

[0108]

[0109] Furthermore, 10,000 new samples, namely the second foundation pit samples, are generated through Monte Carlo sampling, and the trained proxy model is used for prediction to obtain the mean and standard deviation of each response value, and then the robustness index of the foundation pit is calculated. Note that the units of each response value should be unified during calculation, and meters are used as the unit here. The calculation results are shown in Table 3:

[0110] Table 3 is a schematic table of the response value calculation results of the embodiment of the present invention

[0111]

[0112]

[0113] That is, in this embodiment, the robustness index of the foundation pit is obtained to be 0.009889.

[0114] Another aspect of the present invention provides an electronic device, which includes a processor, a network interface and a memory, wherein the processor, the network interface and the memory are interconnected, wherein the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the above-mentioned foundation pit robustness analysis method.

[0115] In the embodiments of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0116] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0117] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0118] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0119] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DRRAM).

[0120] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0121] It should be understood that the system disclosed in the present invention can be implemented in other ways. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the communication connection between modules can be through some interfaces, indirect coupling or communication connection of servers or units, which can be electrical or other forms.

[0122] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each module may exist physically separately, or two or more modules may be integrated into one processing unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional unit.

[0123] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A foundation pit robustness analysis method, characterized in that: The method comprises: S1. After performing random field simulation on the soil property values ​​of the target foundation pit, the soil property values ​​are mapped into the numerical model to obtain a number of first foundation pit samples; the first foundation pit samples include a distribution image of the soil property values ​​and a mean and variance of the soil property values; S2. Calculate the design response mean corresponding to each first foundation pit sample by using the numerical model, label the first foundation pit sample according to the design response mean, and generate a data set; S3, training a proxy model according to the data set to obtain a trained proxy model; S4, repeat S2 to S3 to obtain trained proxy models corresponding to multiple design response means; S5, repeat S1 to obtain a number of second foundation pit samples and then input them into a plurality of trained proxy models to obtain a plurality of design response prediction means; S6. Perform weighted fusion calculation based on the standard deviation and covariance of the predicted mean of each design response to obtain the robustness index of the target foundation pit.

2. A foundation pit robustness analysis method according to claim 1, characterized in that: The random field simulation includes: A random field is constructed based on random parameters of the soil property values ​​using the Monte Carlo sampling method; wherein the random parameters include the mean, variance, coefficient of variation, vertical fluctuation distance and horizontal fluctuation distance of the soil property values.

3. A foundation pit robustness analysis method according to claim 1, characterized in that: The soil property values ​​are selected from any three property values ​​of the soil physical and mechanical properties of the target foundation pit.

4. A foundation pit robustness analysis method according to claim 3, characterized in that: The distribution image of the soil attribute value is an RGB image generated by numerical model conversion, including: The three soil property values ​​of each unit body in the mapped numerical model are converted into R channel values, G channel values ​​and B channel values ​​respectively; Assign the R channel values, G channel values ​​and B channel values ​​of all units to the R channel, G channel and B channel respectively to generate an RGB image.

5. A foundation pit robustness analysis method according to claim 1, characterized in that: The design response mean includes the pile body stress mean, the pile body displacement mean, the pit bottom uplift mean and the surrounding settlement mean.

6. A foundation pit robustness analysis method according to claim 1, characterized in that: The standard deviation of the predicted mean for each design response is given by: Among them, σ i is the standard deviation of the predicted mean of the ith design response, x ik is the predicted mean of the i-th design response corresponding to the k-th second foundation pit sample, is the predicted mean of the i-th design response, and M is the number of samples in the second foundation pit.

7. A foundation pit robustness analysis method according to claim 1, characterized in that: The covariance of the predicted mean for each design response is given by: Among them, Cov(X i ,X j ) is the covariance between the predicted mean of the ith design response and the predicted mean of the jth design response, x ik is the predicted mean of the i-th design response corresponding to the k-th first random field sample, x jk is the predicted mean value of the j-th design response corresponding to the k-th second foundation pit sample, is the predicted mean of the ith design response, is the predicted mean of the j-th design response, and M is the number of samples in the second foundation pit.

8. A foundation pit robustness analysis method according to claim 1, characterized in that: The weight fusion is performed according to the standard deviation and covariance of the predicted mean of each design response, including: The weights are assigned based on the standard deviation of the predicted mean of each design response, calculated as: Among them, ω i is the fusion weight of the predicted mean of the i-th design response, σ i , σ j is the standard deviation of the predicted means of the i-th and j-th design responses, and n is the number of types of the predicted means of the design responses; The fusion calculation is performed according to the weight of each design response prediction mean, and the calculation formula is: Among them, σ p is the robustness index of the target foundation pit, Cov(X i ,X j ) is the covariance between the predicted mean of the ith design response and the predicted mean of the jth design response.

9. A foundation pit robustness analysis method according to claim 1, characterized in that: The proxy model adopts a convolutional neural network.

10. An electronic device, characterized in that: It includes at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a foundation pit robustness analysis method as described in any one of claims 1 to 9.

Citation Information

Patent Citations

  • Foundation pit settlement monitoring system based on numerical analysis and prediction method

    CN111705856A

  • Foundation pit soil parameter inversion method combining PSO-DE algorithm and neural network

    CN113221462A

  • Method for partitioning influence of excavation of foundation pit adjacent to existing structure on surrounding environment

    CN116306120A

  • Foundation pit supporting structure under limited terrain close to old bridge and construction method

    CN116335147A

  • Method and system for detecting compactness performance of concrete in arch bridge tube based on complementary fusion of multi-source acoustic parameter model

    CN117309999A

Cited By

  • Foundation pit deformation prediction method, foundation pit deformation prediction model training method and equipment

    CN119647243A

  • CPTU soil body layering method based on machine learning and uncertainty analysis

    CN120217173A