Stack-pile foundation dynamic feedback optimization method and system based on settlement data driving

Abstract

The invention relates to the technical field of geotechnical engineering, and provides a pile loading-pile foundation dynamic feedback optimization method and system based on settlement data driving. The pile loading-pile foundation dynamic feedback optimization method based on settlement data driving comprises the following steps: constructing a data set based on historical settlement monitoring data; training a settlement prediction model by using the data set to obtain a settlement prediction value corresponding to the field settlement monitoring data; the settlement prediction model is composed of a physical calculation model and a machine learning model, and the settlement prediction value is the sum of a settlement theoretical value calculated by the physical calculation model and a residual value learned by the machine learning model; and a pile foundation scheme meeting the settlement constraint is screened out according to the settlement predicted value, and then the optimal pile foundation scheme is obtained with the shortest construction period and the lowest manufacturing cost as optimization targets. According to the method, an early-stage stacking scheme can be optimized by utilizing prediction data, and the practical applicability of the stacking scheme is improved.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering technology, and in particular to a dynamic feedback optimization method and system for surcharge-pile foundations based on settlement data. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Surcharge pretreatment combined with pile foundation construction is a composite foundation treatment technology for complex geological conditions such as soft soil foundations. Surcharge improves the properties of the foundation soil through consolidation, such as increasing the compression modulus, which directly affects pile foundation settlement; the better the improved soil properties, the smaller the pile foundation settlement. However, due to the strong correlation between surcharge pretreatment and pile foundation settlement, the traditional surcharge pretreatment combined with pile foundation construction mode has many problems, such as strong reliance on experience, blind control of settlement, and unreasonable cost and schedule. The design of surcharge schemes in traditional engineering projects usually relies on experience. If the surcharge is insufficient, the improvement of foundation soil properties is not adequate, and the pile foundation settlement may not meet the engineering requirements. If the surcharge is excessive, such as excessive surcharge intensity or excessive surcharge time, although the settlement control meets the engineering requirements, it will cause problems such as material waste or extended construction period. Therefore, using the traditional method for site surcharge pretreatment may be out of sync with the subsequent pile foundation settlement requirements. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a dynamic feedback optimization method and system for surcharge-pile foundation based on settlement data, which can optimize the previous surcharge scheme using predicted data and improve the practical applicability of the surcharge scheme.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a dynamic feedback optimization method for surcharge-pile foundations based on settlement data.

[0006] In one or more embodiments, a settlement data-driven dynamic feedback optimization method for surcharge-pile foundations is provided, comprising: A dataset is constructed based on historical settlement monitoring data; the samples in the dataset include input parameters and their corresponding settlement values; the input parameters include settlement variation over time, survey and test data of actual soil layers at the site, test data during surcharge, and pile foundation schemes; the pile foundation schemes include design parameters of the surcharge scheme and parameters of the engineering piles; A settlement prediction model is trained using a dataset to obtain the settlement prediction value corresponding to the on-site settlement monitoring data. The settlement prediction model consists of a physical calculation model and a machine learning model. The settlement prediction value is the sum of the theoretical settlement value calculated by the physical calculation model and the residual value learned by the machine learning model. Based on the predicted settlement values, pile foundation schemes that meet the settlement constraints are selected, and then the optimal pile foundation scheme is obtained with the shortest construction period and the lowest cost as the optimization objective.

[0007] A second aspect of the present invention provides a dynamic feedback optimization system for surcharge-pile foundations based on settlement data.

[0008] In one or more embodiments, a settlement data-driven dynamic feedback optimization system for surcharge-pile foundations includes: The dataset construction module is used to build a dataset based on historical settlement monitoring data. The samples in the dataset include input parameters and their corresponding settlement values. The input parameters include the settlement change over time, the survey and test data of the actual soil layers at the site, the test data during surcharge, and the pile foundation scheme. The pile foundation scheme includes the design parameters of the surcharge scheme and the parameters of the engineering piles. The settlement prediction model training module is used to train the settlement prediction model using the dataset to obtain the settlement prediction value corresponding to the on-site settlement monitoring data. The settlement prediction model consists of a physical calculation model and a machine learning model. The settlement prediction value is the sum of the theoretical settlement value calculated by the physical calculation model and the residual value learned by the machine learning model. The pile foundation scheme optimization module is used to select pile foundation schemes that meet settlement constraints based on settlement prediction values, and then obtain the optimal pile foundation scheme with the shortest construction period and lowest cost as the optimization objectives.

[0009] A third aspect of the present invention provides a computer-readable storage medium.

[0010] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described above.

[0011] A fourth aspect of the present invention provides an electronic device.

[0012] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described above.

[0013] Compared with the prior art, the beneficial effects of the present invention are: This invention addresses the problem of the disconnect between the surcharge scheme and the subsequent pile foundation settlement requirements in traditional surcharge pretreatment and pile foundation combined construction. It establishes a surcharge-pile foundation dynamic feedback optimization method driven by settlement data, which uses a physical information neural network to predict pile foundation settlement and uses the predicted data to optimize the early surcharge scheme. Attached Figure Description

[0014] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0015] Figure 1 This is a flowchart of the dynamic feedback optimization method for surcharge-pile foundation based on settlement data according to an embodiment of the present invention; Figure 2 This is a diagram of the dynamic feedback optimization process of surcharge-pile foundation based on settlement data in an embodiment of the present invention. Figure 2 This is a schematic diagram of the physical information neural network model according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the dynamic feedback optimization system for surcharge-pile foundation based on settlement data according to an embodiment of the present invention. Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0017] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, 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 invention pertains.

[0018] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0019] Figure 1 A schematic diagram of the dynamic feedback optimization method for surcharge-pile foundation based on settlement data driven by an embodiment of the present invention is provided. According to... Figure 1 The settlement data-driven dynamic feedback optimization method for surcharge-pile foundation in this embodiment may include the following steps S101 to S103.

[0020] The specific implementation process of steps S101 to S103 is as follows: Step S101: Construct a dataset based on historical settlement monitoring data; the samples in the dataset include input parameters and their corresponding settlement values; the input parameters include settlement variation over time, actual soil layer survey and test data, test data during surcharge (settlement variation over time, pore water pressure) and pile foundation scheme; the pile foundation scheme includes the design parameters of the surcharge scheme and the parameters of the engineering piles.

[0021] Pre-installed monitoring equipment: Install monitoring equipment around the foundation pit; Preset monitoring points: Determine the locations of monitoring points around the foundation pit for real-time data monitoring; Monitoring data: Collect data on geological parameters, pile testing, pile settlement, etc. The value of settlement over time, the actual soil layer survey and test data of the site, such as the void ratio, consolidation coefficient, permeability coefficient, etc., need to be obtained through standardized procedures such as on-site drilling and sampling, and laboratory testing. It is necessary to ensure that the number of test samples for each soil layer is sufficient to improve the representativeness and accuracy of the data. Furthermore, pile foundation design parameters such as pile length and pile diameter are also important components of the dataset, as these data affect the calculation of pile foundation settlement. Through systematic organization, verification, and integration of the above-mentioned various types of data, a complete dataset is ultimately established, providing a reliable foundation for subsequent analysis and simulation.

[0022] Outliers caused by instrument malfunctions or other reasons are removed. For missing values ​​in the dataset, interpolation can be used to extrapolate them, while for data with clear physical meaning, calculations can be performed using relevant physical formulas to ensure that the completed data still reflects the true physical laws. Furthermore, the data is standardized to give each feature equal weight in model training, eliminating interference from differences in units of measurement.

[0023] Finally, the preprocessed dataset is divided into training and test sets according to a reasonable ratio. Typically, the training set comprises 70%-80% and is used for model parameter learning and fitting; the test set comprises 30%-20% and is used to evaluate the model's performance on unseen data. The randomness of the data should be maintained during the partitioning process to avoid distorted model evaluation results due to uneven sample distribution, thus laying the foundation for subsequent model training and optimization.

[0024] Step S102: Train a settlement prediction model using the dataset to obtain the settlement prediction value corresponding to the on-site settlement monitoring data; the settlement prediction model consists of a physical calculation model and a machine learning model, and the settlement prediction value is the sum of the theoretical settlement value calculated by the physical calculation model and the residual value learned by the machine learning model. The theoretical settlement value obtained from the physical calculation model is:

[0025]

[0026]

[0027] in, In the group of piles Settlement of the pile due to its own load; The central pile of a pile group Harmony Stakes The interaction coefficient; For pile group foundation piles The settlement of the pile top; For the settlement of the foundation; Additional stress at the bottom of the foundation; The width of the foundation; The Poisson's ratio of the soil along the pile; The composite compression modulus of the soil beneath the pile cap; This represents the settlement influence coefficient.

[0028] The loss function in the process of training the settlement prediction model consists of data loss and physical loss.

[0029] Data loss is set as :

[0030] in, To monitor the number of data samples; For the first The predicted settlement value corresponding to the input parameters of each sample; For the measured settlement value, For the first Input parameters for each sample.

[0031] The physical loss is:

[0032]

[0033]

[0034]

[0035] in, For displacement compatibility loss; This is the load balance loss; To constrain the settlement of the foundation and the composite modulus; The number of samples calculated for physical loss; For the first The predicted settlement value corresponding to the input parameters of each sample; For the first The measured settlement values ​​of the foundation corresponding to the input parameters of each sample; For the first The first sample input parameter corresponding to the first sample input parameter Predicted load value caused by the self-load of the pile root; For the first Predicted additional load borne by the foundation under the input parameters of each sample; For the first The measured total load value corresponding to each sample input parameter; For the first Predicted settlement values ​​of the foundation corresponding to each sample input parameter; The width of the foundation; This is the settlement influence coefficient; The Poisson's ratio of the soil along the pile; For the first Predicted values ​​of pile-soil composite compression modulus corresponding to the input parameters of each sample; The elastic modulus of the pile body; This is the sum of the cross-sectional areas of all the foundation piles under the pile cap; The area of ​​the foundation; The compression modulus of soil; This represents the total area of ​​the foundation soil beneath the pier cap.

[0036] Step S103: Select the pile foundation scheme that meets the settlement constraints based on the settlement prediction value, and then obtain the optimal pile foundation scheme with the shortest construction period and the lowest cost as the optimization objective.

[0037] The predicted settlement value of the pile foundation is used to optimize the previous surcharge plan. If the predicted settlement value exceeds the maximum settlement value required by the project (this value is determined according to the specification based on the project type), the previous surcharge plan may have problems such as insufficient surcharge or too short a surcharge time. If the predicted settlement value is too small and the degree of consolidation does not meet the specification requirements, the previous surcharge plan may have problems such as excessive surcharge or excessive surcharge time.

[0038] One hundred random loading schemes are generated, ensuring that the loading rate and magnitude constraints are met. For each scheme, the final settlement is calculated using a physical information neural network. > If the solution is deemed "infeasible", it is directly classified as such. The fitness function of a feasible solution is represented by the following equation:

[0039] Where T represents the total surcharge duration and C represents the total surcharge cost. , , As weight; This is the final output of the predicted settlement value for the pile foundation; This refers to the allowable settlement value of the pile foundation for the project; The maximum permissible surcharge period within the feasible range; This represents the maximum permissible stacking cost within the feasible range.

[0040] In determining the optimal pile foundation scheme, the project priority is safety > cost > construction period.

[0041] set up =0.5, =0.2, =0.3. Randomly generate 100 surcharge schemes and determine their feasibility. If the set of feasible solutions is empty, adjust the engineering pile parameters, substitute the adjusted engineering pile parameters into the previous step, regenerate the surcharge schemes, and filter them until a feasible solution is obtained.

[0042] Preferably, the Pareto optimal solution of the feasible solution in terms of "settlement-schedule-cost" is obtained by using the NSGA-II algorithm, and the optimal surcharge parameters and the corresponding engineering pile parameters are finally output.

[0043] like Figure 3 As shown, the settlement data-driven dynamic feedback optimization system for surcharge-pile foundation provided in this embodiment of the invention can be implemented in software. The settlement data-driven dynamic feedback optimization system for surcharge-pile foundation includes the following software modules: dataset construction module 301, settlement prediction model training module 302, and pile foundation scheme optimization module 303.

[0044] The functions of each software module in the settlement data-driven dynamic feedback optimization system for surcharge-pile foundations are described below: The dataset construction module 301 is used to construct a dataset based on historical settlement monitoring data. The samples in the dataset include input parameters and their corresponding settlement values. The input parameters include the settlement change over time, the survey and test data of the actual soil layers at the site, the test data during surcharge, and the pile foundation scheme. The pile foundation scheme includes the design parameters of the surcharge scheme and the parameters of the engineering piles. Settlement prediction model training module 302 is used to train the settlement prediction model using a dataset to obtain the settlement prediction value corresponding to the on-site settlement monitoring data. The settlement prediction model consists of a physical calculation model and a machine learning model. The settlement prediction value is the sum of the theoretical settlement value calculated by the physical calculation model and the residual value learned by the machine learning model. The pile foundation scheme optimization module 303 is used to select pile foundation schemes that meet the settlement constraints based on the settlement prediction value, and then obtain the optimal pile foundation scheme with the shortest construction period and the lowest cost as the optimization objective.

[0045] It should be noted that each module in the settlement data-driven dynamic feedback optimization system for surcharge-pile foundation in this embodiment corresponds one-to-one with each step in the settlement data-driven dynamic feedback optimization method for surcharge-pile foundation in the above embodiment, and their specific implementation processes are the same, so they will not be repeated here.

[0046] The structure of the electronic device according to an embodiment of the present invention will be described in detail below. Figure 4 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention. It can be understood that... Figure 4 The diagram shows only an exemplary structure of the electronic device, not the entire structure. Some or all of the structures shown may be implemented as needed.

[0047] The electronic device provided in this embodiment of the invention includes: at least one processor 401, a memory 402, a user interface 403, and at least one network interface 404. The various components in the settlement data-driven surcharge-pile foundation dynamic feedback optimization system are coupled together via a bus system 405. It can be understood that the bus system 405 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 405 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4 The general designated all buses as Bus System 405.

[0048] The user interface 403 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.

[0049] It is understood that memory 402 can be volatile memory or non-volatile memory, or both. In this embodiment of the invention, memory 402 is capable of storing data to support the operation of the terminal. Examples of this data include any computer programs used to operate on the terminal, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, driver layers, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications.

[0050] In some embodiments, the settlement data-driven dynamic feedback optimization system for surcharge-pile foundations provided in this invention can be implemented using a combination of hardware and software. For example, the settlement data-driven dynamic feedback optimization system for surcharge-pile foundations provided in this invention can be a processor in the form of a hardware decoding processor, programmed to execute the settlement data-driven dynamic feedback optimization method for surcharge-pile foundations provided in this invention. For instance, the hardware decoding processor can employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0051] As an example, processor 401 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0052] As an example of the hardware implementation of the settlement data-driven dynamic feedback optimization system for surcharge-pile foundations provided in this embodiment of the invention, the device provided in this embodiment of the invention can be directly executed by a processor 401 in the form of a hardware decoding processor. For example, it can be executed by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components to implement the settlement data-driven dynamic feedback optimization method for surcharge-pile foundations provided in this embodiment of the invention.

[0053] The memory 402 in this embodiment of the invention is used to store various types of data to support the operation of the settlement data-driven surcharge-pile foundation dynamic feedback optimization system, or to store data for execution. Figure 1The program code for the method shown. Examples of this data include: any executable instructions for operating on a settlement data-driven surcharge-pile dynamic feedback optimization system, such as executable instructions that can be included in the executable instructions to implement the settlement data-driven surcharge-pile dynamic feedback optimization method of the embodiments of the present invention.

[0054] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by the central processing unit, it performs the various functions defined in the apparatus of this application.

[0055] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0056] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A settlement data-driven dynamic feedback optimization method for surcharge-pile foundations, characterized in that, include: A dataset is constructed based on historical settlement monitoring data; the samples in the dataset include input parameters and their corresponding settlement values; the input parameters include settlement variation over time, survey and test data of actual soil layers at the site, test data during surcharge, and pile foundation schemes; the pile foundation schemes include design parameters of the surcharge scheme and parameters of the engineering piles; A settlement prediction model is trained using a dataset to obtain the settlement prediction value corresponding to the on-site settlement monitoring data. The settlement prediction model consists of a physical calculation model and a machine learning model. The settlement prediction value is the sum of the theoretical settlement value calculated by the physical calculation model and the residual value learned by the machine learning model. Based on the predicted settlement values, pile foundation schemes that meet the settlement constraints are selected, and then the optimal pile foundation scheme is obtained with the shortest construction period and the lowest cost as the optimization objective.

2. The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in claim 1, characterized in that, In determining the optimal pile foundation scheme, the fitness function is: Where T represents the total surcharge duration and C represents the total surcharge cost. , , As weight; This is the final output of the predicted settlement value for the pile foundation; This refers to the allowable settlement value of the pile foundation for the project; The maximum permissible surcharge period within the feasible range; This represents the maximum permissible stacking cost within the feasible range.

3. The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in claim 1, characterized in that, In determining the optimal pile foundation scheme, the project priority is safety > cost > construction period.

4. The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in claim 1, characterized in that, The loss function in the process of training the settlement prediction model consists of data loss and physical loss.

5. The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in claim 4, characterized in that, Data loss is set as : in, To monitor the number of data samples; For the first The predicted settlement value corresponding to the input parameters of each sample; For the measured settlement value, For the first Input parameters for each sample.

6. The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in claim 4, characterized in that, The physical loss is: in, For displacement compatibility loss; This is the load balance loss; To constrain the settlement of the foundation and the composite modulus; The number of samples calculated for physical loss; For the first The predicted settlement value corresponding to the input parameters of each sample; For the first The measured settlement values ​​of the foundation corresponding to the input parameters of each sample; For the first The first sample input parameter corresponding to the first sample input parameter Predicted load value caused by the self-load of the pile root; For the first Predicted additional load borne by the foundation under the input parameters of each sample; For the first The measured total load value corresponding to each sample input parameter; For the first Predicted settlement values ​​of the foundation corresponding to each sample input parameter; The width of the foundation; This is the settlement influence coefficient; The Poisson's ratio of the soil along the pile; For the first Predicted values ​​of pile-soil composite compression modulus corresponding to the input parameters of each sample; The elastic modulus of the pile body; This is the sum of the cross-sectional areas of all the foundation piles under the pile cap; The area of ​​the foundation; The compression modulus of soil; This represents the total area of ​​the foundation soil beneath the pier cap.

7. The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in claim 1, characterized in that, The theoretical settlement value obtained from the physical calculation model is: in, In the group of piles Settlement of the pile due to its own load; The central pile of a pile group Harmony Stakes The interaction coefficient; For pile group foundation piles Pile top settlement; For the settlement of the foundation; Additional stress at the bottom of the foundation; The width of the foundation; The Poisson's ratio of the soil along the pile; The composite compression modulus of the soil beneath the pile cap; This represents the settlement influence coefficient.

8. A settlement data-driven dynamic feedback optimization system for surcharge-pile foundations, characterized in that, The settlement data-driven dynamic feedback optimization method for surcharge-pile foundations, as described in any one of claims 1-7, includes: The dataset construction module is used to build a dataset based on historical settlement monitoring data. The samples in the dataset include input parameters and their corresponding settlement values. The input parameters include the settlement change over time, the survey and test data of the actual soil layers at the site, the test data during surcharge, and the pile foundation scheme. The pile foundation scheme includes the design parameters of the surcharge scheme and the parameters of the engineering piles. The settlement prediction model training module is used to train the settlement prediction model using the dataset to obtain the settlement prediction value corresponding to the on-site settlement monitoring data. The settlement prediction model consists of a physical calculation model and a machine learning model. The settlement prediction value is the sum of the theoretical settlement value calculated by the physical calculation model and the residual value learned by the machine learning model. The pile foundation scheme optimization module is used to select pile foundation schemes that meet settlement constraints based on settlement prediction values, and then obtain the optimal pile foundation scheme with the shortest construction period and lowest cost as the optimization objectives.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the settlement data-driven dynamic feedback optimization method for surcharge-pile foundations as described in any one of claims 1-7.

Images