A calculation method for flexible support pile foundation system
By calculating the soil wet risk index and pile foundation stability index, and dynamically adjusting the penalty coefficient of the support vector regression model, the problem of pile length prediction deviation in traditional models is solved, and the prediction accuracy and construction efficiency of the flexible bracket pile foundation system are improved.
Patent Information
- Application Number
- CN202411244697.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-06
Smart Images

Figure CN118761140B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of flexible supports, and in particular to a calculation method for a flexible support pile foundation system. Background Art
[0002] Flexible support pile foundation system is an efficient and adaptable engineering structure, mainly used to support and stabilize various structures. This system combines a series of flexible supports and pile foundations to form a stable support structure that can adapt to different terrain and environmental conditions, including complex geology and large terrain fluctuations. Flexible support pile foundation systems usually have a large span and high clearance, which reduces the occupation of land, while reducing the difficulty and cost of construction. They are designed with simple installation methods, improve construction efficiency, and have good wind resistance and reliability.
[0003] Different foundation conditions require different parameters of the flexible support pile foundation system. When installing on a foundation with poor supporting capacity, the length of the pile needs to be increased to avoid insufficient supporting capacity; when installing on a foundation with good supporting capacity, the length of the pile needs to be reduced to reduce costs. The length of the pile can be obtained based on the foundation soil data and the pile foundation system design parameters according to historical construction records. The support vector regression model can be used to predict the length of the pile based on these data to avoid the inability to obtain the length of the pile due to the loss of construction records.
[0004] When using the traditional support vector regression (SVR) model to predict pile length based on foundation data and design parameters of the flexible support pile foundation system, the fixed penalty coefficient C cannot be adjusted according to the data, resulting in deviations in the predicted pile length. Summary of the invention
[0005] In order to solve the above technical problems, the present application provides a calculation method for a flexible support pile foundation system to solve the existing problems.
[0006] A calculation method for a flexible support pile foundation system in this application adopts the following technical solution:
[0007] An embodiment of the present application provides a method for calculating a flexible support pile foundation system, the method comprising the following steps:
[0008] Collect soil parameters and pile foundation design parameters of the area to be installed for each flexible support pile foundation, wherein the soil parameters include soil collapsibility coefficient, soil compression coefficient, annual rainfall and soil moisture content, and the pile foundation design parameters include the total number of pile foundations in the area to be installed for each flexible support pile foundation, the piling position of each pile foundation and the theoretical diameter;
[0009] Based on the similarity between soil parameters, the soil wetting risk index of each flexible support pile foundation to be installed area is obtained; based on the pile foundation design parameters of each flexible support pile foundation to be installed area, the pile foundation stability index of each flexible support pile foundation to be installed area is obtained;
[0010] Based on the soil collapsibility risk index and pile foundation stability index, the adaptive penalty coefficient of each flexible support pile foundation to be installed area is obtained;
[0011] Based on the total number of pile foundations in the area to be installed for each flexible support pile foundation, the pile driving position of each pile foundation and the theoretical diameter, the diameter sequence and the spacing sequence are obtained; based on the soil parameters, the diameter sequence, the spacing sequence, the soil collapsibility risk index and the pile foundation stability index, the characteristic matrix of the area to be installed for each flexible support pile foundation is obtained;
[0012] Based on the feature matrix, the feature vectors and labels of the feature vectors of the areas to be installed of each flexible support pile foundation are obtained; based on the feature vectors, the labels of the feature vectors and the adaptive penalty coefficients, the trained SVR model is obtained; and based on the trained SVR model, the length of the pile is obtained.
[0013] Furthermore, the method for obtaining the soil collapsibility risk index is:
[0014] Soil moisture correlation factors obtained based on similarities between soil parameters;
[0015] Based on soil moisture related factors and soil parameters, the moisture influencing factors of the areas where each flexible support pile foundation is to be installed are obtained;
[0016] For each flexible support pile foundation to be installed area, the product of the moisture influencing factor, soil collapsibility coefficient and soil compression coefficient of the flexible support pile foundation to be installed area is calculated, and the normalized value of the product result is used as the soil collapsibility risk index of each flexible support pile foundation to be installed area.
[0017] Furthermore, the method for obtaining the soil moisture content related factor is:
[0018] The soil collapsibility coefficients of all the areas where the flexible support pile foundations are to be installed are combined into a soil collapsibility coefficient sequence, and the soil compression coefficient, annual rainfall and soil water content are processed using the same method as the soil collapsibility coefficient to obtain a soil compression coefficient sequence, an annual rainfall sequence and a soil water content sequence;
[0019] The similarity between the annual rainfall series and the soil moisture series was calculated as the soil moisture correlation factor.
[0020] Further, the method for obtaining the moisture influencing factor is:
[0021] For each flexible support pile foundation to be installed area, the product of the soil moisture content related factor, soil moisture content and annual precipitation is calculated as the moisture influencing factor of each flexible support pile foundation to be installed area.
[0022] Furthermore, the formula of the pile foundation stability index is: ; Wherein, Z represents the pile foundation stability index of the area to be installed in the flexible support pile foundation, M represents the total number of preset installation pile foundations in the area to be installed in the flexible support pile foundation, represents the theoretical diameter of the i-th pile foundation in the area where the flexible support pile foundation is to be installed, It represents the distance between the i-th pile and the i+1-th pile in the area where the flexible support pile is to be installed, and norm() is the normalization function.
[0023] Furthermore, the formula of the adaptive penalty coefficient is: ; Where C represents the adaptive penalty coefficient of the flexible support pile foundation to be installed, N represents the total number of flexible support pile foundation to be installed, , They represent the pile foundation stability index and soil collapse risk index of the jth flexible support pile foundation to be installed area, is the preset adjustment factor.
[0024] Furthermore, the diameter sequence and the spacing sequence are obtained by:
[0025] The average value of the diameters of the flexible support pile foundations to be installed in the areas to be installed of each flexible support pile foundation is calculated as the mean diameter value, and the average value of the distances between the piles is calculated as the mean spacing value. The sequence composed of the mean diameters of all the flexible support pile foundations to be installed is calculated as the diameter sequence, and the sequence composed of the mean spacing values is calculated as the spacing sequence.
[0026] Furthermore, the method for obtaining the feature matrix is:
[0027] The sequence composed of soil collapse risk indexes of all flexible support pile foundations to be installed is used as the first sequence, and the pile foundation stability indexes of all flexible support pile foundations to be installed are used as the second sequence;
[0028] The soil collapsibility coefficient sequence, soil compression coefficient sequence, annual rainfall sequence, soil moisture content sequence, diameter sequence, spacing sequence, first sequence and second sequence are taken as rows of the feature matrix to construct the feature matrix.
[0029] Furthermore, the trained SVR model includes:
[0030] All feature vectors and labels of feature vectors are used as input to train a support vector regression model, and the adaptive penalty coefficient is used as the penalty coefficient of the support vector regression model to obtain a trained SVR model.
[0031] Further, obtaining the length of the pile based on the trained SVR model includes:
[0032] The soil collapsibility coefficient, soil compression coefficient, annual rainfall and soil moisture content of the area where the flexible support pile foundation is to be installed, as well as the total number of pile foundations, the piling position of each pile foundation and the theoretical diameter are input into the trained SVR model to output the predicted pile length.
[0033] This application has at least the following beneficial effects:
[0034] This application calculates the soil wetting risk index based on the soil conditions of the area where the flexible support pile foundation system is to be installed, calculates the pile foundation stability index based on the design parameters of the pile foundation, calculates the adaptive penalty coefficient C based on the indicators of all areas, and trains the SVR model to obtain the length of the piles of the flexible support pile foundation system to be installed.
[0035] The beneficial effect is that the selection of the penalty coefficient when training the SVR model takes into account the soil conditions in the area where the flexible support pile foundation system is to be installed and the design parameters of the pile foundation itself in the actual scenario, avoiding errors in the length of the pile predicted by the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0037] Figure 1 A flow chart of a calculation method for a flexible support pile foundation system provided in this application;
[0038] Figure 2 Get a flow chart for adaptive penalty coefficients. DETAILED DESCRIPTION
[0039] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the calculation method of a flexible support pile foundation system proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0041] The specific scheme of the calculation method of a flexible support pile foundation system provided by the present application is described in detail below with reference to the accompanying drawings.
[0042] An embodiment of the present application provides a method for calculating a flexible support pile foundation system. Specifically, the following method for calculating a flexible support pile foundation system is provided. Figure 1 , the method comprises the following steps:
[0043] Step S1, collecting soil parameters and pile foundation design parameters of the area where each flexible support pile foundation is to be installed.
[0044] Currently, there are N areas that need to install flexible support pile foundation systems, and these areas are far apart, and the soil moisture content and rainfall in the areas are quite different. In this embodiment, the value of N is 50.
[0045] For each flexible support pile foundation installation area, obtain soil parameters, including:
[0046] Soil samples are collected from the areas where each flexible support pile foundation is to be installed, and the soil collapsibility coefficient and soil compression coefficient of the soil in the areas where each flexible support pile foundation is to be installed are calculated. The calculation of the soil collapsibility coefficient and soil compression coefficient belongs to the known technology, and the specific process will not be repeated here.
[0047] The annual rainfall in the previous year in the area where each flexible support pile foundation is to be installed is obtained from the meteorological data network, and the soil moisture content in the area where each flexible support pile foundation is to be installed at the current moment is collected using a soil moisture sensor.
[0048] The sequence composed of the soil collapsibility coefficients of all the flexible support pile foundation installation areas is taken as the soil collapsibility coefficient sequence. The soil compression coefficient, annual rainfall and soil moisture content of all the flexible support pile foundation installation areas are processed using the same method as the soil collapsibility coefficient to obtain the soil compression coefficient sequence, annual rainfall sequence and soil moisture content sequence.
[0049] For each flexible support pile foundation installation area, obtain the pile foundation design parameters, including:
[0050] When piling is performed in the area to be installed for each flexible support pile foundation, the total number of pile foundations in the area to be installed for the flexible support pile foundation and the piling position of each pile foundation are obtained through the geological survey report, and the theoretical diameter of each pile foundation is obtained according to the engineering design planning report. Among them, the method for obtaining the total number of pile foundations in the area to be installed for each flexible support pile foundation, the piling position of each pile foundation and the theoretical diameter is a well-known technology and will not be described in detail here.
[0051] Calculate the average value of the diameters of the piles of the flexible support pile foundation system to be installed in the area to be installed of each flexible support pile foundation as the mean diameter, and the average value of the distances between the piles as the mean spacing. Calculate the sequence composed of the average diameters of all the areas to be installed of the flexible support pile foundation as the diameter sequence, and the sequence composed of the mean spacings as the spacing sequence.
[0052] Step S2, based on soil parameters, obtain the soil wetting risk index of each flexible support pile foundation to be installed area; based on the pile foundation design parameters of each flexible support pile foundation to be installed area, obtain the pile foundation stability index of each flexible support pile foundation to be installed area; based on the soil wetting risk index and the pile foundation stability index, obtain the adaptive penalty coefficient of each flexible support pile foundation to be installed area.
[0053] Collapsible foundation is a special type of soil. This type of soil is uniform but loose in structure. When it is not soaked in water, the soil has low compressibility and relatively high strength. However, when it is soaked in water with a certain pressure, the structure of this type of soil will be quickly destroyed, causing the soil to sink significantly and the strength to be greatly reduced, which will lead to uneven settlement of the flexible support pile foundation system, affecting the stability and service life of the entire structure. Due to the special properties of collapsible foundation, the flexible support pile foundation system must take this foundation condition into consideration when designing it. The anti-collapse ability of the pile foundation can be enhanced by increasing the length of the pile.
[0054] The length of the pile is affected by the supporting force of the collapsible foundation and the resistance of the flexible support itself. If the pile is too short, it cannot achieve the expected supporting effect and may easily cause deformation and uneven force on the pile foundation system. Although the supporting force of the pile is better if it is too long, the construction difficulty and cost will increase.
[0055] In order to control costs and reduce construction difficulty, a support vector regression (SVR) model is trained according to the soil conditions of the construction site and the design parameters of the flexible support itself to predict the length of the pile. On the basis of ensuring that the pile has sufficient support, the length of the pile is reduced, the construction difficulty is reduced, and the cost is reduced.
[0056] The penalty coefficient C in support vector regression is a key parameter, which determines the model's tolerance for prediction errors. A larger penalty coefficient means that the model has a lower tolerance for errors, which may lead to overfitting, making the model output a more appropriate length of piles on the training data, while the predicted length of piles in the test data has a larger error. A smaller penalty coefficient means that the model has a higher tolerance for errors, which often introduces more errors, leading to underfitting, resulting in a larger error in the predicted length of the pile.
[0057] Therefore, in order to obtain a more accurate pile length, a more appropriate penalty coefficient C can be calculated based on the soil conditions in the area where the flexible support pile foundation system is to be installed and the design parameters of the flexible support itself, so that the pile length predicted by the support vector regression model is more appropriate.
[0058] As the main way of water replenishment in nature, rainfall has a direct and far-reaching impact on soil collapsibility. In arid or semi-arid areas, the amount and frequency of rainfall will directly affect the moisture state of the soil, and thus its collapsibility. Generally speaking, when rainfall is heavy or concentrated, the soil easily absorbs water, causing its structure to be rapidly destroyed, increasing the risk of collapsibility. In particular, loosely structured soils such as loess are prone to significant collapsible deformation under the action of water, which not only affects the stability of the surface, but may also cause damage to buildings and other infrastructure.
[0059] There is a great correlation between rainfall and soil water content, but the soil water content will increase significantly when the rainfall is heavy or concentrated, and will decrease after rainfall or in dry seasons. The soil water content is closely related to the length of the pile. Areas with high water content require longer piles to provide stronger support.
[0060] The currently collected soil moisture content cannot be used as a reference for the length of the pile, because soil moisture content is often related to rainfall, and the soil in different regions is affected by rainfall to different degrees, because the rate of soil moisture loss in different regions is different. If the currently collected soil moisture content is used as the training data for SVR, without considering the rapid increase in soil moisture caused by rainfall, the predicted pile length will be too short, which may cause insufficient support.
[0061] Therefore, it is necessary to first calculate the soil moisture content correlation factor to characterize the relationship between the soil moisture content and rainfall in the area where each flexible support pile foundation is to be installed, so as to better represent the soil collapsibility. The calculation method is: calculate the correlation between the annual rainfall sequence and the soil moisture content sequence as the soil moisture content correlation factor. This embodiment uses the Pearson correlation coefficient as the correlation calculation method, and the implementer can choose other similarity calculation methods.
[0062] The larger the value of the soil moisture correlation factor is, the stronger the correlation between the soil moisture content and the annual precipitation is, that is, the stronger the correlation between the current soil moisture content and the annual precipitation in the area where each flexible support pile foundation is to be installed is. On the contrary, it means that the correlation between them is weak, and the relationship between the soil moisture content and the annual precipitation in the area where each flexible support pile foundation is to be installed is weak, which may be due to the rapid loss of moisture in the soil.
[0063] Based on the above analysis, the moisture influencing factor of each flexible support pile foundation to be installed is calculated by taking into account the soil moisture content of each flexible support pile foundation to be installed area and the annual precipitation of each flexible support pile foundation to be installed area, as well as the relationship between soil moisture content and annual precipitation. The calculation method is: ; In the formula, SI represents the moisture influencing factor of the area to be installed of each flexible support pile foundation, TS represents the soil moisture content of the area to be installed of each flexible support pile foundation at the current moment, NS represents the annual precipitation of the area to be installed of each flexible support pile foundation, and R represents the soil moisture content related factor.
[0064] The moisture influencing factor takes into account the impact of soil moisture content on soil supporting capacity, and also takes into account the impact of annual precipitation on soil moisture content. By calculating the correlation coefficient between them, it characterizes the statistical correlation between soil moisture content and rainfall, and expresses the dynamic changes of soil moisture content.
[0065] The larger the moisture impact factor, the greater the moisture content of the soil in the area where each flexible support pile foundation is to be installed under the influence of rainfall. Even if the current soil moisture content is small, it may reach a relatively large soil moisture content after rainfall. On the contrary, it means that the soil moisture content in the area where each flexible support pile foundation is to be installed is small. Even in the case of rainfall, the change in soil moisture content will be small, so the impact on soil support will be small.
[0066] The supporting capacity of soil is not only affected by rainfall and soil moisture content, but also by the properties of the soil itself in the area where each flexible support pile foundation is to be installed. Among them, the most influential are the soil collapsibility coefficient and soil compression coefficient.
[0067] Soil collapsibility coefficient: refers to the ratio of the height difference of a soil sample before and after immersion in water to the original height of the soil sample under a certain pressure. Soil compression coefficient: refers to the property of soil that its volume can shrink under pressure, and is defined as the ratio of the volume strain increment of a soil sample to the compressive stress increment.
[0068] It should be noted that the soil collapsibility coefficient and the soil compression coefficient can be obtained by experimental calculation of collected soil samples, and the process will not be repeated in this embodiment.
[0069] The larger the soil collapsibility coefficient, the greater the soil moisture content. The greater the soil collapsibility in the area where the flexible support pile foundation is to be installed, the smaller the supporting effect on the flexible support, and the longer the pile length needs to be to avoid deformation and uneven force. The larger the soil compression coefficient, the more likely the soil is to be compressed and settled under load, and its supporting capacity is smaller.
[0070] The soil collapsibility risk index is calculated by combining the moisture influencing factor of each flexible support pile foundation installation area and the soil collapsibility coefficient and soil compression coefficient of each flexible support pile foundation installation area. The formula is: ; In the formula, for each flexible support pile foundation to be installed area, F represents the soil collapsibility risk index of the flexible support pile foundation to be installed area, SI represents the moisture influencing factor of the flexible support pile foundation to be installed area, SX represents the soil collapsibility coefficient of the flexible support pile foundation to be installed area, YS represents the soil compression coefficient of the flexible support pile foundation to be installed area, and norm() represents the normalization function.
[0071] The larger the soil collapsibility risk index is, the smaller the soil support in the area where each flexible support pile foundation is to be installed is, and the greater the possibility of soil collapsibility is, and the longer the length of the flexible support pile foundation system piles installed in the area where the flexible support pile foundation is to be installed should be; on the contrary, the stronger the soil support in the area where each flexible support pile foundation is to be installed is, the shorter the length of the piles should be.
[0072] In addition to being affected by the supporting properties of the soil in the installation area, the length of the pile is also affected by the design parameters of the flexible bracket itself. The larger the diameter of the pile, the stronger the supporting effect and the greater the ability to resist soil wetting. Similarly, the closer the distance between the piles, the stronger the supporting effect and the greater the ability to resist soil wetting.
[0073] Furthermore, combined with the design parameters of the flexible support pile foundation system itself, the pile foundation stability index of each flexible support pile foundation to be installed area is calculated, and the formula is: ; In the formula, for each flexible support pile foundation to be installed area, Z represents the pile foundation stability index of the flexible support pile foundation to be installed area, i represents the i-th pile foundation in the flexible support pile foundation to be installed area, M represents the total number of preset installation pile foundations in the flexible support pile foundation to be installed area, represents the preset diameter of the i-th pile foundation in the area where the flexible support pile foundation is to be installed, represents the preset distance between the ith pile foundation and the i+1th pile foundation in the area where the flexible support pile foundation is to be installed, and norm() represents the normalization function.
[0074] It should be noted that the above distance is no longer calculated for the last pile. This embodiment uses Euclidean distance as the distance measurement method, and the implementer can use other distance measurement methods according to actual conditions.
[0075] The larger the pile foundation stability index is, the more stable the combination of piles in the pile foundation system is, that is, the larger the diameter of the pile is or the closer the distance between the piles is, which means that it is less likely to deform or be subjected to uneven force on a collapsible foundation. On the premise of ensuring stability, the length of the pile can be reduced to reduce the difficulty and cost of construction. On the contrary, it means that the stability of the pile foundation system itself is poor, and the length of the pile should be increased to avoid deformation or uneven force on the flexible bracket due to collapsible foundation.
[0076] The soil collapsibility risk index reflects the complexity of soil conditions, that is, the supporting effect on the flexible support pile foundation system. The larger its value, the greater the possibility of soil collapsibility, and a larger penalty coefficient is needed to learn the relationship between soil conditions and pile length to avoid underfitting.
[0077] The pile foundation stability index reflects the stability of the flexible support pile foundation system design. The larger its value, the more stable it is when the pile length is constant. Therefore, in order to reduce the construction difficulty and cost, the pile length can be reduced. At this time, a smaller penalty coefficient is needed to avoid overfitting the model due to training data, and the predicted pile length is too long, which fails to achieve the stated purpose.
[0078] The parameters of the support vector regression model are adjusted by combining the soil collapsible risk index and the pile foundation stability index to obtain the adaptive penalty coefficient C. One calculation method is: ; In the above formula, C represents the adaptive penalty coefficient, N represents the total number of areas where the flexible support pile foundation is to be installed, , They represent the pile foundation stability index and soil collapse risk index of the j-th flexible support pile foundation system, represents a preset adjustment factor, and the penalty coefficient C is adjusted to a suitable value range. In this embodiment, the value is 10. The adaptive penalty coefficient acquisition flow chart is as follows: Figure 2 shown.
[0079] Step S3, training a support vector regression model according to the obtained adaptive penalty coefficient, and using the trained model input data to obtain the length of the pile of the flexible support pile foundation system to be installed.
[0080] The sequence composed of soil collapse risk indexes of all flexible support pile foundations to be installed is taken as the first sequence, and the pile foundation stability indexes of all flexible support pile foundations to be installed are taken as the second sequence.
[0081] The characteristic matrix is constructed using soil collapsibility coefficient sequence, soil compression coefficient sequence, annual rainfall sequence, soil moisture content sequence, pile diameter sequence and pile spacing sequence of the flexible support pile foundation system, as well as the first sequence and the second sequence as rows of the characteristic matrix.
[0082] Each column of data in the feature matrix is used as the feature vector of the corresponding flexible support pile foundation to be installed area, and the optimal pile length in each flexible support pile foundation to be installed area is obtained from the historical construction records, and the optimal pile length is used as the label of the feature vector of each flexible support pile foundation to be installed area.
[0083] The feature vector and label are used as input to train the support vector regression model. The other parameters are set as follows: the penalty coefficient C is the adaptive penalty coefficient calculated in step S2, the kernel function is the radial basis function, and the kernel function parameter is 0.2, the optimization algorithm is the quadratic programming algorithm, and the loss function is -Insensitive loss function. After training, the trained SVR model is obtained.
[0084] The soil collapsibility coefficient, soil compression coefficient, annual rainfall and soil moisture content of the area where the flexible support pile foundation is to be installed, as well as the total number of pile foundations, the piling position of each pile foundation and the theoretical diameter are input into the trained model, and the predicted pile length is output to complete a calculation method for a flexible support pile foundation system.
[0085] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0086] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0087] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Modifications to the technical solutions recorded in the aforementioned embodiments, or equivalent replacement of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A calculation method for a flexible support pile foundation system, characterized in that: The method comprises the following steps: Collect soil parameters and pile foundation design parameters of the area to be installed for each flexible support pile foundation, wherein the soil parameters include soil collapsibility coefficient, soil compression coefficient, annual rainfall and soil moisture content, and the pile foundation design parameters include the total number of pile foundations in the area to be installed for each flexible support pile foundation, the piling position of each pile foundation and the theoretical diameter; Based on the similarity between soil parameters, the soil wetting risk index of each flexible support pile foundation to be installed area is obtained; based on the pile foundation design parameters of each flexible support pile foundation to be installed area, the pile foundation stability index of each flexible support pile foundation to be installed area is obtained; Based on the soil collapsibility risk index and pile foundation stability index, the adaptive penalty coefficient of each flexible support pile foundation to be installed area is obtained; Based on the total number of pile foundations in the area to be installed for each flexible support pile foundation, the pile driving position of each pile foundation and the theoretical diameter, the diameter sequence and the spacing sequence are obtained; based on the soil parameters, the diameter sequence, the spacing sequence, the soil collapsibility risk index and the pile foundation stability index, the characteristic matrix of the area to be installed for each flexible support pile foundation is obtained; Based on the feature matrix, the feature vectors and labels of the feature vectors of the areas to be installed of each flexible support pile foundation are obtained; based on the feature vectors, the labels of the feature vectors and the adaptive penalty coefficients, the trained SVR model is obtained; based on the trained SVR model, the length of the pile is obtained; The method for obtaining the soil collapsibility risk index is as follows: Soil moisture content correlation factors obtained based on similarities between soil parameters; Based on soil moisture related factors and soil parameters, the moisture influencing factors of the areas where each flexible support pile foundation is to be installed are obtained; For each flexible support pile foundation to be installed area, calculate the product of the moisture influence factor, soil collapsibility coefficient and soil compression coefficient of the flexible support pile foundation to be installed area, and use the normalized value of the product result as the soil collapsibility risk index of each flexible support pile foundation to be installed area; The method for obtaining the soil moisture content related factor is: The soil collapsibility coefficients of all the areas where the flexible support pile foundations are to be installed are combined into a soil collapsibility coefficient sequence, and the soil compression coefficient, annual rainfall and soil water content are processed using the same method as the soil collapsibility coefficient to obtain a soil compression coefficient sequence, an annual rainfall sequence and a soil water content sequence; The similarity between the annual rainfall series and the soil moisture series was calculated as the soil moisture correlation factor; The method for obtaining the moisture influencing factor is: For each flexible support pile foundation to be installed area, the product of soil moisture content related factor, soil moisture content and annual precipitation is calculated as the moisture influencing factor of each flexible support pile foundation to be installed area; The formula of the pile foundation stability index is: ; Wherein, Z represents the pile foundation stability index of the area to be installed in the flexible support pile foundation, M represents the total number of preset installation pile foundations in the area to be installed in the flexible support pile foundation, represents the theoretical diameter of the i-th pile foundation in the area where the flexible support pile foundation is to be installed, represents the distance between the i-th pile and the i+1-th pile in the area where the flexible support pile is to be installed, and norm() is a normalization function; The formula of the adaptive penalty coefficient is: ; Where C represents the adaptive penalty coefficient of the flexible support pile foundation to be installed, N represents the total number of flexible support pile foundation to be installed, , They represent the pile foundation stability index and soil collapse risk index of the jth flexible support pile foundation to be installed area, is the preset adjustment factor; The method for obtaining the diameter sequence and the spacing sequence is: Calculate the average value of the diameters of the flexible support piles to be installed in the area to be installed of each flexible support pile as the mean diameter value, and the average value of the distances between the piles as the mean spacing value, and use the sequence composed of the average diameters of all the areas to be installed of the flexible support piles as the diameter sequence, and the sequence composed of the average spacing values as the spacing sequence; The method for obtaining the feature matrix is: The sequence composed of soil collapsibility risk indexes of all flexible support pile foundations to be installed is used as the first sequence, and the pile foundation stability indexes of all flexible support pile foundations to be installed are used as the second sequence; The soil collapsibility coefficient sequence, soil compression coefficient sequence, annual rainfall sequence, soil moisture content sequence, diameter sequence, spacing sequence, first sequence and second sequence are taken as rows of the feature matrix to construct the feature matrix.
2. A calculation method for a flexible support pile foundation system as claimed in claim 1, characterized in that: The trained SVR model includes: All feature vectors and feature vector labels are used as input to train a support vector regression model, and the adaptive penalty coefficient is used as the penalty coefficient of the support vector regression model to obtain a trained SVR model.
3. A calculation method for a flexible support pile foundation system as claimed in claim 1, characterized in that: The obtaining the length of the pile based on the trained SVR model includes: The soil collapsibility coefficient, soil compression coefficient, annual rainfall and soil moisture content of the area where the flexible support pile foundation is to be installed, as well as the total number of pile foundations, the piling position of each pile foundation and the theoretical diameter are input into the trained SVR model to output the predicted pile length.
Citation Information
Patent Citations
Method for reasonably burying bridge pile foundation deep in loess zone
CN101994320A
Method and system for evaluating vertical bearing capacity of pile foundation
CN113957933A
Energy pile green low-carbon building design method based on machine learning
CN115935477A
Dehumidification system humidity prediction method and system based on improved SVR
CN116415208A
Cross-sea bridge pile foundation construction quality digital management method
CN116993229A
