Pile body strength prediction method, equipment, medium and product

Abstract

The invention provides a pile body strength prediction method, equipment, a medium and a product, and relates to the technical field of geotechnical engineering. The pile body strength prediction method comprises the steps that a parameter random field corresponding to each soil body parameter is determined based on investigation data, wherein the investigation data comprises the soil body parameter corresponding to each drilling position in a to-be-analyzed area; obtaining soil body parameters of the target pile body according to the parameter random field; the soil body parameters and the construction process parameters of the target pile body are input into a pile body strength prediction model, the pile body strength is determined according to the output result of the pile body strength prediction model, and the pile body strength prediction model is obtained based on historical site investigation data and historical construction process data training proxy model. According to the embodiment of the invention, the error between the prediction result and the actual pile body strength can be reduced, the possibility of engineering safety control errors is reduced, and the safety of the engineering object in the service stage is improved.

Description

Technical Field

[0001] The present application relates to the field of geotechnical engineering technology, and more specifically, to a pile strength prediction method, equipment, medium and product. Background Art

[0002] DCM (Deep cement mixture) is a process in which a curing agent is forcibly stirred into the soil. After the curing agent hardens, a composite with a certain strength is formed in the soil. DCM is widely used in various geotechnical engineering foundation treatments (such as bridge construction, house construction, etc.).

[0003] In projects using DCM technology, the strength of DCM piles is related to the safety of the project objects using DCM piles during the service phase. Therefore, knowing the strength of DCM piles in advance is crucial for the safety control of projects using DCM. The strength of conventional DCM piles is determined by indoor mix tests. However, due to the difference between the soil parameters of indoor tests and on-site soils, the pile strength obtained through indoor mix tests is very different from the actual strength of the mixing piles on site. It is difficult to accurately represent the actual strength of the piles, which can easily lead to errors in project safety control and affect the safety of the project objects during the service phase. Summary of the invention

[0004] The embodiments of the present application provide a pile strength prediction method, device, medium and product, which can solve the problem that the pile strength determined by the existing indoor mixing method is very different from the actual on-site mixing pile strength, which easily leads to engineering safety control errors and affects the safety of the engineering object during the service stage. In order to achieve this purpose, the embodiments of the present application provide the following solutions.

[0005] According to one aspect of an embodiment of the present application, a pile strength prediction method is provided, comprising:

[0006] Determining a parameter random field corresponding to each soil parameter based on survey data, wherein the survey data includes soil parameters corresponding to each drilling position in the area to be analyzed;

[0007] Acquire soil parameters of the target pile body according to the parameter random field;

[0008] The soil parameters and the construction process parameters of the target pile are input into a pile strength prediction model, and the pile strength is determined according to the output result of the pile strength prediction model, wherein the pile strength prediction model is obtained by training an agent model based on historical site survey data and historical construction process data.

[0009] In a possible implementation, determining the parameter random field corresponding to each soil parameter based on the survey data includes:

[0010] Acquire a cross-correlation matrix between different soil parameters according to the survey data, and acquire an autocorrelation matrix corresponding to the area to be analyzed according to the range information of the area to be analyzed;

[0011] A parameter random field corresponding to each soil parameter is obtained according to the mutual correlation matrix and the autocorrelation matrix.

[0012] In a possible implementation, the step of obtaining a cross-correlation matrix between different soil parameters according to the survey data includes:

[0013] The mutual correlation coefficients between different soil parameters are obtained, and the mutual correlation matrix is ​​generated based on the mutual correlation coefficients.

[0014] In a possible implementation, the range information includes the depth and the length and width of the area to be analyzed on a horizontal plane, and acquiring the autocorrelation matrix corresponding to the area to be analyzed according to the range information of the area to be analyzed includes:

[0015] Generate vectors corresponding to the length, the width, and the depth according to the range information;

[0016] An autocorrelation matrix is ​​obtained according to the vector and autocorrelation distance information, wherein the autocorrelation distance information is determined based on the survey data.

[0017] In a possible implementation, the obtaining a parameter random field corresponding to each soil parameter according to the mutual correlation matrix and the autocorrelation matrix includes:

[0018] Obtaining the lower triangular matrix of the cross-correlation matrix and the autocorrelation matrix after Levsky decomposition;

[0019] The parameter random field corresponding to each soil parameter is determined according to the lower triangular matrix, the random number corresponding to the soil parameter and the preset number of simulations, and the number of the parameter random fields of each soil parameter corresponds to the preset number of simulations.

[0020] In a possible implementation, the step of acquiring soil parameters of a target pile body according to the parameter random field includes:

[0021] Obtaining the construction position coordinates of the target pile body;

[0022] The soil parameters corresponding to the target pile body in each parameter random field are obtained according to the construction position coordinates.

[0023] In a possible implementation, it also includes:

[0024] The data of the pile strength are obtained according to the preset number of simulations, and the mean and variance of the pile strength are calculated based on the data.

[0025] According to one aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0026] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0027] According to one aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0028] The beneficial effects of the technical solution provided by the embodiment of the present application are:

[0029] The pile strength prediction method provided in the present application includes determining a parameter random field corresponding to each soil parameter based on survey data; obtaining soil parameters of the target pile according to the parameter random field; inputting the soil parameters and the construction process parameters of the target pile into a pile strength prediction model obtained by training an agent model based on historical site survey data and historical construction process data. The embodiment of the present application uses survey data to obtain the soil parameters of the target pile, and uses historical data of engineering construction to obtain a pile strength prediction model. The strength data of the target pile is predicted based on the soil parameters and the pile strength prediction module. Compared with the indoor mix test method, it is closer to the actual construction environment, can reduce the error between the prediction result and the actual pile strength, reduce the possibility of engineering safety control errors, and improve the safety of the engineering object during the service phase. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in describing the embodiments of the present application.

[0031] Figure 1 A flowchart of a pile strength prediction method provided in an embodiment of the present application;

[0032] Figure 2 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0034] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation of other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the present technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" indicates that it is implemented as "A", or is implemented as "A", or is implemented as "A and B".

[0035] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0036] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0037] The pile strength prediction method, equipment, medium and product provided in this application are intended to solve at least one technical problem existing in the prior art.

[0038] A pile strength prediction method is provided in an embodiment of the present application. The device to which the pile strength prediction method is applied may be a mobile phone, a computer, a server, or other objects that can obtain survey data and calculate pile strength based on the survey data.

[0039] Alternatively, if Figure 1 As shown, the pile strength prediction method includes:

[0040] S101: Determine a parameter random field corresponding to each soil parameter based on the survey data.

[0041] Optionally, the area where the pile to be predicted is located can be determined as the area to be analyzed, and survey data can be obtained by drilling holes in the area to be analyzed. The survey data includes soil parameters corresponding to each drilling position.

[0042] Optionally, the soil parameters include water content, density, saturation, particle size, plasticity index, organic matter content, cone penetration test (CPT) value, cohesion, internal friction angle, autocorrelation distance, and variance of each soil parameter.

[0043] Optionally, the soil parameters corresponding to the drilling position are data within a preset diameter range centered on the drilling position. The preset diameter may be 2 meters, 3 meters, 4 meters, or other values, which are not limited here.

[0044] In one embodiment, holes are drilled in a discrete distribution in the area to be analyzed to obtain soil samples within a 3-meter diameter range centered on the drilling position, and soil parameters are collected using the soil samples. According to the type of soil parameters, corresponding testing methods can be used on the soil samples to obtain corresponding soil parameters.

[0045] Optionally, since the survey boreholes in the area to be analyzed are discretely distributed, and the pile strength prediction is a continuous prediction in the construction site, and there is correlation between soil parameters and each parameter has variability in space, it is necessary to obtain an internally continuous soil parameter field that takes into account parameter variability. Wherein, the parameter random field corresponding to each soil parameter is determined based on the survey data, including: obtaining the cross-correlation matrix between different soil parameters according to the survey data, and obtaining the autocorrelation matrix corresponding to the area to be analyzed according to the range information of the area to be analyzed; obtaining the parameter random field corresponding to each soil parameter according to the cross-correlation matrix and the autocorrelation matrix.

[0046] Optionally, the range information includes the length and width of the area to be analyzed on the horizontal plane and the depth of the area to be analyzed. The depth can be determined according to the depth of the pile body inserted into the ground, wherein the depth of the area to be analyzed is greater than the depth of the pile body inserted into the ground.

[0047] Optionally, the soil parameters at the same drilling position can be used as a group of test data, and the correlation between different soil parameters can be obtained by comparing the results of different groups of test data. Obtaining the cross-correlation matrix between different soil parameters according to the survey data includes: obtaining the cross-correlation coefficients between different soil parameters, and generating the cross-correlation matrix based on the cross-correlation coefficients.

[0048] Alternatively, the correlation coefficients between different soil parameters can be calculated using formula (1).

[0049]

[0050] Among them, γ xy represents the mutual correlation coefficient between soil parameter x and soil parameter y, N represents the number of test data corresponding to soil parameter x or y when calculating the mutual correlation coefficient, x irepresents the i-th test data i in the soil parameter x, represents the average value of soil parameters x, y i represents the soil parameter j in a set of test data, Represents the average value of soil parameter y.

[0051] In one embodiment, the cross-correlation matrix can be Γ=[γ xy ] n×n , Γ is an n-order square matrix, where n is the number of soil parameters.

[0052] Optionally, the autocorrelation matrix corresponding to the area to be analyzed is obtained according to the range information of the area to be analyzed, including: generating vectors corresponding to the length, width and depth according to the range information; and obtaining the autocorrelation matrix according to the vectors and autocorrelation distance information, wherein the autocorrelation distance information is determined based on the survey data.

[0053] Optionally, the length, width and depth each correspond to a vector, and the elements in the vector are arranged in an arithmetic progression. The difference between adjacent elements in different vectors can be adjusted according to the size of the area to be analyzed, the precision requirement of the pile strength, the number of holes, and other data. For example, the higher the precision requirement, the smaller the difference.

[0054] Optionally, the autocorrelation distance includes at least one of a horizontal autocorrelation distance and a vertical autocorrelation distance, wherein the vertical autocorrelation distance may be a preset multiple of the horizontal autocorrelation distance.

[0055] Optionally, the value of the horizontal autocorrelation distance may be within a first preset range, and the size of the preset multiple may be within a second preset range. The sizes of the first preset range and the second preset range may be determined according to actual needs.

[0056] In one embodiment, the horizontal length x, width y and depth z of the area to be analyzed are determined according to the range of the area to be analyzed, and a vector X'=[0,x step ,…,x](x step represents the difference between adjacent elements), Y'=[0,y step ,…,y](y step represents the difference between adjacent elements), Z'=[0,z step ,…,z](z step represents the difference between adjacent elements), where x step ,y step Not more than 0.5m, z step Less than 0.2m. According to vectors X', Y', and Z', the autocorrelation matrix [ρ x ,ij]、[ρ y ,ij]、[ρ z, ij], the calculation expression is:

[0057]

[0058] Among them, x i 、x j From the vector X', [ρ x ,ij] represents x i 、x j The autocorrelation distance between i ,y j From the vector Y', [ρ y ,ij] represents y i ,y j The autocorrelation distance between i 、z j From the vector Z', [ρ z ,ij] represents z i 、z j The autocorrelation distance between h ,θ v They are the horizontal autocorrelation distance and the vertical autocorrelation distance respectively. The horizontal autocorrelation distance can be determined as 0.5-2m based on the survey data, and the vertical autocorrelation distance can be determined as 5-10 times of the horizontal autocorrelation distance.

[0059] Optionally, a parameter random field corresponding to each soil parameter is obtained according to the mutual correlation matrix and the autocorrelation matrix, including: obtaining the lower triangular matrix after Lesky decomposition of the mutual correlation matrix and the autocorrelation matrix; determining the parameter random field corresponding to each soil parameter according to the lower triangular matrix, the random numbers corresponding to the soil parameters and the preset number of simulations, and the number of parameter random fields for each soil parameter corresponds to the preset number of simulations.

[0060] In one embodiment, L r is the lower triangular matrix of the cross-correlation matrix Γ of soil parameters after Levski decomposition, L x , L y , L z They are the autocorrelation matrices [ρ x，ij ]、[ρ y，ij ]、[ρ z，ij ] is the lower triangular matrix after Leski decomposition. Input the above lower triangular matrix into formula (3) to obtain the parameter random field:

[0061]

[0062] Among them, X n is the parameter random field of the nth soil parameter, U n is a random number generated based on the mean and variance of the nth soil parameter. Represents the convolution operation. The parameter random field of water content (P1), density (P2), saturation (P3), particle size (P4), plasticity index (P5), organic matter content (P6), CPT value (P7), cohesion (P8), and internal friction angle (P9) is obtained through formula (3). The parameter random field includes soil parameters at any position in the area to be analyzed.

[0063] Optionally, multiple values ​​may be taken for each soil parameter at each drilling position according to a preset number of simulations, and the number of values ​​of the soil parameter may correspond to the preset number of simulations. When obtaining the parameter simulation field, the soil parameters are divided into multiple groups based on the preset number of simulations, and each group of data includes a value data of the soil parameter at each drilling position. When obtaining the parameter random field according to the preset number of simulations, a group of data is used each time to obtain a parameter random field.

[0064] Optionally, the preset number of simulations may be greater than 500, and the preset number of simulations may also be greater than other thresholds, the size of which may be determined based on the stability of the pile strength prediction results (i.e., it is necessary to ensure that when the preset number of simulations is greater than the threshold, the prediction results meet the stability requirements).

[0065] In one embodiment, the preset number of simulations is M, M is greater than 1000, and the random numbers corresponding to different soil parameters also change with the mean and variance of the soil parameters. The mean and variance can be determined based on the values ​​of the soil parameters corresponding to all drilling positions. For example, when the soil parameter is water content, the water content of all drilling positions is obtained, and the mean and variance are calculated based on the water content. Multiple parameter simulation fields of the soil parameters are obtained by multiple calculations using formula (3).

[0066] S102: Obtain soil parameters of the target pile body according to the parameter random field.

[0067] Optionally, acquiring soil parameters of the target pile body according to the parameter random field includes: acquiring construction position coordinates of the target pile body; and acquiring soil parameters corresponding to the target pile body in each parameter random field according to the construction position coordinates.

[0068] Optionally, to improve the accuracy of pile strength prediction, when obtaining soil parameters of the target pile, after obtaining the construction position coordinates of the target pile, each parameter simulation field is used to obtain the soil parameters at the position corresponding to the construction position coordinates.

[0069] Optionally, the acquisition range of the soil parameters (such as the depth range of the soil parameters) may be determined according to the type of the target pile and the depth at which the target pile is inserted into the ground.

[0070] In one embodiment, the construction position coordinates of the target pile body are (x l ,y l), obtain the parameter random field of the soil parameter simulation for the mth time, and extract the plane position (x l ,y l )Soil parameters within the depth range of 0 to zl.

[0071] S103: Input soil parameters and construction process parameters of the target pile into a pile strength prediction model, and determine the pile strength according to an output result of the pile strength prediction model.

[0072] Optionally, the pile strength prediction model is obtained by training the proxy model based on historical site survey data and historical construction process data, wherein the historical site survey data and historical construction process data can be obtained through DCM case data.

[0073] In one embodiment, the historical site survey data includes soil parameters at the drilling position in the DCM case, the historical construction process data includes at least one of the curing agent dosage, water-cement ratio, mixing times, penetration speed, drill rod speed, and motor current within the depth range of the DCM pile body, and the DCM case data also includes the pile strength test values ​​corresponding to the historical site survey data and the historical construction process data. The soil parameters and construction process data are used as independent variables, and the pile strength test values ​​are used as dependent variables to train the proxy model, and the proxy model can be selected from any one of random forest, support vector machine, and neural network.

[0074] Optionally, in order to ensure the accuracy of the agent model training, the data volume of the training samples formed by the historical site survey data and the historical construction process data should be greater than a preset threshold, which may be 2000.

[0075] Optionally, in order to ensure that the soil parameters, construction process parameters, and pile strength match in space, the construction process parameters of the DCM pile and the sampling location of the pile strength should take the data within the diameter of 3m of the drilling position to ensure that the discreteness of the sample data is smaller.

[0076] Optionally, the construction process parameters of the target pile body can be obtained during the construction of the target pile body. During the construction process, the changes in the curing agent dosage, water-cement ratio, mixing times, penetration speed, drill rod speed, and motor current along the depth of the mixing pile are recorded. The type of curing agent is set according to construction requirements.

[0077] Optionally, since there are multiple parameter random fields, in order to improve the stability of the prediction results, the pile strength prediction is performed based on the soil parameters corresponding to each parameter random field. After obtaining the pile strength prediction result, the mean and variance of the pile strength prediction result are obtained, and the mean and variance are used to indicate the pile strength.

[0078] In one embodiment, soil parameters within the depth range of 0 to z1 at the plane position (xl, yl) are extracted according to the coordinates of the construction position of the mixing pile in the parameter random field obtained in each simulation. The construction process parameters and the soil parameters extracted each time are input into the pile strength prediction model, which outputs the corresponding mixing pile 0 to z1. l Predicted values ​​of pile strength within the depth range. The mean and variance are calculated based on the predicted values ​​of DCM pile strength for M times, where M is greater than 1000.

[0079] The pile strength prediction method of the embodiment of the present application includes determining a parameter random field corresponding to each soil parameter based on survey data; obtaining soil parameters of the target pile according to the parameter random field; inputting the soil parameters and the construction process parameters of the target pile into a pile strength prediction model obtained by training an agent model based on historical site survey data and historical construction process data. The embodiment of the present application uses survey data to obtain the soil parameters of the target pile, and uses historical data of engineering construction to obtain a pile strength prediction model. The strength data of the target pile is predicted based on the soil parameters and the pile strength prediction module. Compared with the indoor mix test method, it is closer to the actual construction environment, can reduce the error between the prediction result and the actual pile strength, reduce the possibility of engineering safety control errors, and improve the safety of the engineering object during the service phase.

[0080] In an optional embodiment, an electronic device is provided, such as Figure 2 As shown, Figure 2 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0081] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0082] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0083] Memory 4003 can be ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it can be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disc, optical disk, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium, other magnetic storage devices or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation here.

[0084] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0085] Among them, the electronic device can be any electronic product that can interact with an object, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0086] The electronic device may also include a network device and / or an object device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0087] The network where the electronic device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN), etc.

[0088] An embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0089] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0090] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that shown or described in the drawings.

[0091] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0092] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A pile strength prediction method, characterized in that: include: Determining a parameter random field corresponding to each soil parameter based on survey data, wherein the survey data includes soil parameters corresponding to each drilling position in the area to be analyzed; Acquire soil parameters of the target pile body according to the parameter random field; The soil parameters and the construction process parameters of the target pile are input into a pile strength prediction model, and the pile strength is determined according to the output result of the pile strength prediction model, wherein the pile strength prediction model is obtained by training an agent model based on historical site survey data and historical construction process data.

2. The pile strength prediction method according to claim 1, characterized in that: The step of determining the parameter random field corresponding to each soil parameter based on the survey data includes: Obtaining a cross-correlation matrix between different soil parameters according to the survey data, and obtaining an autocorrelation matrix corresponding to the area to be analyzed according to the range information of the area to be analyzed; A parameter random field corresponding to each soil parameter is obtained according to the mutual correlation matrix and the autocorrelation matrix.

3. The pile strength prediction method according to claim 2, characterized in that: The step of obtaining a cross-correlation matrix between different soil parameters according to the survey data includes: The mutual correlation coefficients between different soil parameters are obtained, and the mutual correlation matrix is ​​generated based on the mutual correlation coefficients.

4. The pile strength prediction method according to claim 2, characterized in that: The range information includes the depth of the area to be analyzed and the length and width on the horizontal plane. The step of obtaining the autocorrelation matrix corresponding to the area to be analyzed according to the range information of the area to be analyzed includes: Generate vectors corresponding to the length, the width, and the depth according to the range information; An autocorrelation matrix is ​​obtained according to the vector and autocorrelation distance information, wherein the autocorrelation distance information is determined based on the survey data.

5. The pile strength prediction method according to claim 2, characterized in that: The step of obtaining a parameter random field corresponding to each soil parameter according to the mutual correlation matrix and the autocorrelation matrix includes: Obtaining the lower triangular matrix of the cross-correlation matrix and the autocorrelation matrix after Levsky decomposition; The parameter random field corresponding to each soil parameter is determined according to the lower triangular matrix, the random number corresponding to the soil parameter and the preset number of simulations, and the number of the parameter random fields of each soil parameter corresponds to the preset number of simulations.

6. The pile strength prediction method according to claim 5, characterized in that: The step of obtaining soil parameters of a target pile body according to the parameter random field includes: Obtaining the construction position coordinates of the target pile body; The soil parameters corresponding to the target pile body in each parameter random field are obtained according to the construction position coordinates.

7. The pile strength prediction method according to claim 5, characterized in that: Also includes: The data of the pile strength are obtained according to the preset number of simulations, and the mean and variance of the pile strength are calculated based on the data.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images