Prediction method and device for compressive ultimate bearing capacity of offshore photovoltaic tubular pile

Abstract

The invention relates to a method and device for predicting the compressive ultimate bearing capacity of an offshore photovoltaic tubular pile, and relates to the technical field of offshore photovoltaic.The method comprises the steps that a tubular pile compressive static load test system under an offshore photovoltaic scene is constructed, based on a tubular pile compression resistance static load test system, tubular pile sinkage and tubular pile resilience of the test tubular piles of different sizes are determined; determining the ultimate compressive bearing capacities of the test tubular piles of different sizes according to the sinking amounts of the tubular piles, and determining the rebound rates of the test tubular piles of different sizes according to the rebound amounts of the tubular piles; inputting the compressive ultimate bearing capacity of the tubular pile and the rebound rate of the tubular pile into a preset service environment prediction model to obtain a service environment prediction result which can be borne by the test tubular piles with different sizes; and matching corresponding target mounting areas for the test pipe piles with different sizes from the candidate mounting areas. According to the invention, accurate matching of the mounting area of the test pipe pile is realized.

Description

Technical Field

[0001] This disclosure relates to the field of offshore photovoltaic technology, and more specifically, to a method and device for predicting the compressive ultimate bearing capacity of offshore photovoltaic pipe piles. Background Technology

[0002] With the vigorous development of the offshore photovoltaic industry, the application of pile foundation columns in offshore energy engineering has gradually become more widespread. In practical applications, prestressed high-strength concrete pipe piles can be selected for pile foundation columns. Among them, prestressed high-strength concrete pipe piles are a type of pile that has begun to be used in recent years. They are manufactured using pre-tensioning prestressing technology and centrifugal molding. At the same time, due to their advantages such as high degree of factory production, low construction noise pollution, good pile quality, and high strength, they have been widely used at home and abroad.

[0003] Analyzing the compressive bearing capacity of pipe piles helps determine their application under different service environments, thereby ensuring the smooth implementation of offshore photovoltaic projects. Currently, relying solely on specific data provided by manufacturers makes it impossible to accurately determine the ultimate compressive bearing capacity of the test pipe piles, thus reducing the accuracy of the matched target installation area.

[0004] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method and device for predicting the compressive ultimate bearing capacity of pipe piles for offshore photovoltaic systems, thereby overcoming, to some extent, the problem of low accuracy of the target installation area due to limitations and defects in related technologies.

[0006] According to one aspect of this disclosure, a method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems is provided, comprising:

[0007] A static load test system for pipe piles under offshore photovoltaic scenarios was constructed, and the settlement and rebound of pipe piles of different sizes were determined based on the static load test system.

[0008] The ultimate compressive bearing capacity of test pipe piles of different sizes is determined based on the settlement amount of the pipe piles, and the rebound rate of test pipe piles of different sizes is determined based on the rebound amount of the pipe piles.

[0009] The ultimate compressive bearing capacity and rebound rate of the pipe pile are input into a preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear.

[0010] The current environmental parameters of the candidate installation area for the pipe pile to be installed are obtained, and based on the service environment prediction results and the current environmental parameters, the corresponding target installation area is matched from the candidate installation area for test pipe piles of different sizes.

[0011] In one exemplary embodiment of this disclosure, a static load test system for pipe piles under offshore photovoltaic scenarios is constructed, comprising:

[0012] Load the original reference frame model, original experimental pipe pile model, original anchor pile model, and original jack model required for constructing the static load test system for pipe piles in the offshore photovoltaic scenario from the preset BIM model library.

[0013] The original reference frame model, original experimental pipe pile model, original anchor pile model, and original jack model are subjected to model refinement processing to obtain the target reference frame model, target experimental pipe pile model, target anchor pile model, and target jack model.

[0014] Based on the target reference frame model, target experimental pipe pile model, target anchor pile model, and target jack model, the pipe pile static load test system is constructed.

[0015] In one exemplary embodiment of this disclosure, determining the settlement and rebound of test pipe piles of different sizes based on a static load test system for pipe piles includes:

[0016] Select any test pipe pile of different sizes as the target pipe pile;

[0017] The target jack model in the static load test system for pipe pile compression is used to apply different levels of static sinking load to the target pipe pile in order to obtain the first pipe pile sinking amount and the first pipe pile rebound amount under the action of different levels of static sinking load.

[0018] The process of determining the settlement and rebound of the first pipe pile is repeated sequentially to obtain the settlement and rebound of other pipe piles (excluding the target pipe pile) among the test pipe piles of different sizes.

[0019] In one exemplary embodiment of this disclosure, determining the ultimate compressive bearing capacity of test pipe piles of different sizes based on the settlement of the pipe pile includes:

[0020] Obtain the pipe pile compressive strength index curve model associated with the test pipe pile;

[0021] Based on the pipe pile compressive strength index curve model and the pipe pile settlement under different levels of static settlement load, static settlement load-pipe pile settlement curves for test pipe piles of different sizes are constructed.

[0022] The static settlement load-settlement curves of test pipe piles of different sizes were fitted to determine the ultimate compressive bearing capacity of test pipe piles of different sizes.

[0023] In one exemplary embodiment of this disclosure, determining the rebound rate of test pipe piles of different sizes based on the rebound amount includes:

[0024] Based on the settlement and rebound of the pipe piles, the maximum settlement and rebound of test pipe piles of different sizes are determined, and the ratio between the maximum settlement and the maximum rebound is calculated.

[0025] The rebound rate of test pipe piles of different sizes is determined based on the ratio between the maximum settlement and the maximum rebound.

[0026] In one exemplary embodiment of this disclosure, the preset service environment prediction model includes a first embedding mapping layer, an encoding layer, and a hybrid expert model;

[0027] The ultimate compressive bearing capacity and rebound rate of the pipe piles are input into a pre-set service environment prediction model to obtain the predicted service environment conditions that test pipe piles of different sizes can withstand, including:

[0028] Based on the ultimate compressive bearing capacity, rebound rate, and material parameters of test pipe piles of different sizes, the basic information to be predicted is generated, and the context information to be predicted is generated based on the preset model prompts.

[0029] The first embedding mapping layer is used to perform embedding mapping processing on the basic information to be predicted to obtain the pipe pile features, and the first embedding mapping layer is used to perform embedding mapping processing on the context information to be predicted to obtain the context flag sequence.

[0030] The features of the pipe pile and the context flag sequence are encoded based on the coding layer to obtain the overall context representation. Then, the service environment is predicted based on the context flag sequence and the overall context representation using a hybrid expert model to obtain the predicted service environment that the test pipe pile can bear.

[0031] In one exemplary embodiment of this disclosure, the hybrid expert model includes a gated network model and multiple expert neural network models;

[0032] Specifically, the service environment prediction is performed based on the context flag sequence and the overall context representation using a hybrid expert model, resulting in a predicted service environment that the test pipe pile can withstand, including:

[0033] Based on the gating network model and the context flag sequence, the first model weights of the multiple expert neural network models for performing environmental prediction tasks in the weather environment dimension, the second model weights for performing environmental prediction tasks in the marine environment dimension, and the third model weights for performing environmental prediction tasks in the seabed rock and soil dimension are determined.

[0034] Based on the first model weight, the second model weight, and the third model weight, the first target network model required to perform the environmental prediction task in the weather environment dimension, the second target network model required to perform the environmental prediction task in the seawater environment dimension, and the third target network model required to perform the environmental prediction task in the seabed rock and soil dimension are determined from the multiple expert neural network models.

[0035] The context flag sequence and the overall context representation are input into the first target network model, the second target network model and the third target network model respectively to obtain the first environmental prediction result in the weather environment dimension, the second environmental prediction result in the seawater environment dimension and the third environmental prediction result in the seabed rock and soil dimension.

[0036] Based on the first environmental prediction results, the second environmental prediction results, and the third environmental prediction results, the service environment prediction results that the test pipe piles of different sizes can withstand are generated.

[0037] In one exemplary embodiment of this disclosure, based on the service environment prediction results and current environmental parameters, matching corresponding target installation areas for test pipe piles of different sizes from candidate installation areas includes:

[0038] The current environmental parameters and service environment prediction results are encoded based on a preset word vector embedding model to obtain the current environmental feature vector and the service environment feature vector.

[0039] Calculate the feature similarity between the current environment feature vector and the service environment feature vector, and match the corresponding target installation area for test pipe piles of different sizes from the candidate installation areas based on the feature similarity.

[0040] In one exemplary embodiment of this disclosure, the preset word vector embedding model includes multiple Transformer models and an average pooling layer; wherein, encoding the current environment parameters based on the preset word vector embedding model to obtain the current environment feature vector includes:

[0041] Word embedding is performed on the current environment parameters to obtain the word embedding vector, word embedding matrix, and position embedding matrix of the current environment parameters;

[0042] Based on the character embedding vector, character embedding matrix, and position embedding matrix, an embedding vector is generated, and the embedding vector is input into the first Transformer model to generate the first text semantic vector corresponding to the first Transformer model.

[0043] The first text semantic vector is input into the second Transformer model to generate the second text semantic vector corresponding to the second Transformer model. The process of generating the second text semantic vector is repeated in turn to obtain the text semantic vectors corresponding to other Transformer models.

[0044] The first current encoding vector of the current environment parameters is generated based on the text semantic vector and embedding vector corresponding to each Transformer model, and the first current encoding vector is input into the average pooling layer to obtain the current environment feature vector.

[0045] According to one aspect of this disclosure, a device for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems is provided, comprising:

[0046] The pipe pile settlement determination module is used to construct a pipe pile compressive static load test system for offshore photovoltaic scenarios, and to determine the pipe pile settlement and rebound of test pipe piles of different sizes based on the pipe pile compressive static load test system.

[0047] The compressive ultimate bearing capacity determination module is used to determine the compressive ultimate bearing capacity of test pipe piles of different sizes based on the settlement of the pipe pile, and to determine the rebound rate of test pipe piles of different sizes based on the rebound amount of the pipe pile.

[0048] The service environment prediction result determination module is used to input the ultimate compressive bearing capacity and rebound rate of the pipe pile into the preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear.

[0049] The target installation area determination module is used to obtain the current environmental parameters of the candidate installation areas for the pipe piles to be installed, and based on the service environment prediction results and the current environmental parameters, to match the corresponding target installation areas for test pipe piles of different sizes from the candidate installation areas.

[0050] This disclosure provides a method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems. On one hand, it constructs a static load test system for pipe piles in an offshore photovoltaic scenario, and determines the settlement and rebound of test pipe piles of different sizes based on this system. Then, it determines the ultimate compressive bearing capacity of test pipe piles of different sizes based on the settlement, and the rebound rate of test pipe piles of different sizes based on the rebound rate. Finally, it inputs the ultimate compressive bearing capacity and rebound rate into a preset service environment prediction model to obtain the predicted service environment conditions that test pipe piles of different sizes can withstand. Finally, it obtains the current environmental parameters of the candidate installation area for pipe pile installation and, based on the service environment conditions... Based on the service environment prediction results and current environmental parameters, corresponding target installation areas are matched from candidate installation areas for test pipe piles of different sizes. This enables accurate calculation of the ultimate compressive bearing capacity of the test pipe piles, solving the problem in existing technologies where the accuracy of the matched target installation areas is reduced due to the inability to accurately determine the ultimate compressive bearing capacity of the test pipe piles. On the other hand, since corresponding target installation areas can be matched from candidate installation areas for test pipe piles of different sizes based on the service environment prediction results and current environmental parameters, installation areas with different environments can be matched for pipe piles of different sizes, thereby achieving precise installation of the target pipe piles and ensuring the smooth implementation of offshore photovoltaic projects.

[0051] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0053] Figure 1 The flowchart schematically illustrates a method for predicting the ultimate compressive bearing capacity of a pipe pile for offshore photovoltaic systems according to an exemplary embodiment of the present disclosure.

[0054] Figure 2 The diagram schematically illustrates a structural example of a preset service environment prediction model according to an exemplary embodiment of the present disclosure.

[0055] Figure 3 An example diagram illustrating a hybrid expert model according to an exemplary embodiment of the present disclosure is shown.

[0056] Figure 4The flowchart schematically illustrates a specific training process for a pre-defined service environment prediction model according to an example embodiment of the present disclosure.

[0057] Figure 5 The diagram schematically illustrates a structural example of a static load test system for pipe piles in an offshore photovoltaic scenario according to an exemplary embodiment of the present disclosure.

[0058] Figure 6 An example diagram illustrating a static settlement load-settlement curve of a pipe pile according to an exemplary embodiment of the present disclosure is shown.

[0059] Figure 7 The diagram illustrates an example curve obtained by fitting a static settlement load-settlement curve of a pipe pile according to an exemplary embodiment of the present disclosure.

[0060] Figure 8 The diagram illustrates a scenario example of a compression settling-rebound curve according to an exemplary embodiment of the present disclosure.

[0061] Figure 9 The diagram schematically illustrates a structural example of a device for predicting the ultimate compressive bearing capacity of a pipe pile for offshore photovoltaic systems according to an exemplary embodiment of the present disclosure.

[0062] Figure 10 An electronic device is illustrated in accordance with an example embodiment of the present disclosure for predicting the ultimate compressive bearing capacity of pipe piles for realizing offshore photovoltaic systems. Detailed Implementation

[0063] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0064] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0065] In recent years, the bearing capacity of PHC (Prestressed High-Strength Concrete) pipe piles has attracted much attention. Many scholars have conducted research on the bearing capacity of PHC pipe piles through field tests, laboratory tests, and theoretical analyses, achieving certain results. In some methods for analyzing compressive bearing capacity, the bearing capacity of PHC pipe piles of different sizes under different depth conditions has been evaluated and compared using standard penetration tests, static cone penetration tests, and static load tests. In other methods, the bearing capacity of pile foundations in clay under scour conditions has been estimated using the next finite element limit analysis, concluding that the bearing capacity of the pile foundation decreases significantly with increasing scour depth. Some schemes have used field tests and numerical simulations to study the stress and deformation of PHC (Prestressed High-Strength Concrete) pipe pile composite foundations and analyzed the variation law of the pile-soil load sharing ratio. However, none of the above schemes have comprehensively analyzed the compressive bearing capacity of the pipe piles. Furthermore, although the conditions for large-scale and commercial development of offshore photovoltaics have been initially met, how to comprehensively analyze the compressive bearing capacity of pipe piles and plan, design, construct, and operate offshore photovoltaics based on the analysis results is an urgent problem to be solved.

[0066] Based on this, this exemplary embodiment first provides a method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems. This method can run on terminal devices, servers, server clusters, or cloud servers, etc. Of course, those skilled in the art can also run the method disclosed herein on other platforms as needed, and this exemplary embodiment does not impose any special limitations on this. Specifically, refer to... Figure 1 As shown, the method for predicting the ultimate compressive bearing capacity of the pipe piles for offshore photovoltaic systems may include the following steps:

[0067] Step S110. Construct a static load test system for pipe piles under offshore photovoltaic scenarios, and determine the settlement and rebound of pipe piles of different sizes based on the static load test system for pipe piles.

[0068] Step S120. Determine the ultimate compressive bearing capacity of test pipe piles of different sizes based on the settlement amount of the pipe piles, and determine the rebound rate of test pipe piles of different sizes based on the rebound amount of the pipe piles.

[0069] Step S130. Input the ultimate compressive bearing capacity and rebound rate of the pipe pile into the preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear.

[0070] Step S140. Obtain the current environmental parameters of the candidate installation area for the pipe pile to be installed, and based on the service environment prediction results and the current environmental parameters, match the corresponding target installation area for the test pipe piles of different sizes from the candidate installation area.

[0071] In the aforementioned method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems, on the one hand, a static load test system for pipe piles under offshore photovoltaic scenarios is constructed, and the settlement and rebound of test pipe piles of different sizes are determined based on this system. Then, the ultimate compressive bearing capacity of test pipe piles of different sizes is determined based on the settlement, and the rebound rate is determined based on the rebound rate. Finally, the ultimate compressive bearing capacity and rebound rate are input into a pre-set service environment prediction model to obtain the predicted service environment conditions that test pipe piles of different sizes can withstand. Finally, the current environmental parameters of the candidate installation area for pipe pile installation are obtained, and the prediction is based on the service environment conditions. Based on the predicted service environment and current environmental parameters, the system matches target installation areas for test pipe piles of different sizes from the candidate installation areas. This enables precise calculation of the ultimate compressive bearing capacity of the test pipe piles, solving the problem in existing technologies where the accuracy of the matched target installation areas is reduced due to the inability to accurately determine the ultimate compressive bearing capacity of the test pipe piles. On the other hand, since the system can match target installation areas for test pipe piles of different sizes from the candidate installation areas based on the predicted service environment and current environmental parameters, it can match installation areas for different environments for pipe piles of different sizes, thereby achieving precise installation of the target pipe piles and ensuring the smooth implementation of offshore photovoltaic projects.

[0072] The following will further explain and illustrate the method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems, as described in the exemplary embodiments of this disclosure, with reference to the accompanying drawings.

[0073] First, the preset service environment prediction model involved in the exemplary embodiments of this disclosure will be explained and described. Specifically, refer to... Figure 2As shown, the preset service environment prediction model may include a first input layer 201, a first embedding mapping layer 202, an encoding layer 203, a hybrid expert model 204, and a first output layer 205; wherein, reference Figure 3 As shown, the hybrid expert model described here may include a gated network model and multiple expert neural network models; furthermore, the role of each model layer in the service environment prediction process will be detailed later, and will not be elaborated further here.

[0074] In one example embodiment, reference is made to... Figure 4 As shown, the specific training process of the preset service environment prediction model described herein may include the following steps:

[0075] Step S410: Obtain the current material parameters, current service environment parameters, and the ultimate compressive bearing capacity and rebound rate of the installed pipe pile; wherein, the current service environment parameters include the current weather environment parameters, the current seawater environment parameters, and the current seabed soil and rock environment parameters.

[0076] Step S420: Input the current material parameters, the ultimate compressive bearing capacity of the installed pipe pile, and the rebound rate of the pipe pile into the large model to be trained to obtain the first current prediction result in the weather environment dimension, the second current prediction result in the seawater environment dimension, and the third current prediction result in the seabed rock and soil dimension.

[0077] Step S430: Construct a first loss function based on the first current prediction result and the current weather environment parameters; construct a second loss function based on the second current prediction result and the current seawater environment parameters; and construct a third loss function based on the third current prediction result and the current seabed rock and soil environment parameters.

[0078] Step S440: Construct a target loss function based on the first loss function, the second loss function, and the third loss function, and adjust the parameters in the large model to be trained based on the target loss function to obtain the preset service environment prediction model.

[0079] The following will explain and illustrate steps S410-S440. Specifically, the current material parameters recorded here refer to the material parameters used in preparing the installed pipe pile and the dimensional parameters of the installed pipe pile, etc. Taking the installed pipe pile as a PHC (Pre-stressed High-strength Concrete) pipe pile as an example, the specific material parameters can be obtained from the manufacturer of the pipe pile, and this example does not impose any special restrictions on this. The current service environment parameters recorded here may include the weather environment parameters and seawater environment parameters during the service of the installed pipe pile, as well as the physical environment parameters of the seabed soil and rock layers in the installation area where the installed pipe pile is located, etc. The ultimate compressive bearing capacity and rebound rate of the pipe pile recorded here can be calculated based on the static load test system for pipe pile compressive strength. Furthermore, the physical environment parameters of the seabed soil and rock layers recorded above are shown in Table 1 below:

[0080] Table 1

[0081]

[0082] Where γ is the specific gravity; N is the average number of standard penetration tests (SPT) blows; E s c is the compressive modulus; c is the cohesive force. f is the internal friction angle; ak This represents the characteristic value of bearing capacity; "-" indicates that it was not provided in the survey report.

[0083] Furthermore, the constructed loss function can be referenced as shown in the following formulas (1)-(4):

[0084] Loss(θ label1 ,θ label2 ,θ label3 )=mLoss1+nLoss2+hLoss3; Formula (1)

[0085]

[0086] Where Loss(θ) label1 ,θ label2 ,θ label3 ) represents the objective loss function, Loss1 represents the first loss function, Loss2 represents the second loss function, and θ represents the third loss function; N represents the total number of installed pipe piles; label1 As the first current prediction result, θ label2 As the second current prediction result, θ label3 This is the third current prediction result; f(x) i ,θ label1 f(x) represents the process of determining the first current prediction result. i,θ label2 f(x) represents the process of determining the second current prediction result; i ,θ label3 ) represents the process of determining the third current prediction result, y label1 y label2 and y label3 The current weather environment parameters, current seawater environment parameters, and current seabed soil and rock environment parameters are respectively represented by m, n, and h, which represent the weight values ​​of the weather environment dimension, seawater environment dimension, and seabed soil and rock environment dimension, respectively. In actual applications, m, n, and h can be selected according to actual needs, and this example does not impose any special restrictions on them.

[0087] The following will combine Figures 2-4 right Figure 1 The method for predicting the ultimate compressive bearing capacity of the pipe piles for offshore photovoltaic systems, as shown in the example, will be further explained and illustrated. Specifically:

[0088] In step S110, a static load test system for pipe piles under marine photovoltaic scenarios is constructed, and the settlement and rebound of pipe piles of different sizes are determined based on the static load test system for pipe piles.

[0089] In this example embodiment, firstly, a static load test system for pipe piles under offshore photovoltaic scenarios is constructed. Specifically, this can be achieved as follows: The original reference frame model, original experimental pipe pile model, original anchor pile model, and original jack model required for constructing the static load test system for pipe piles under offshore photovoltaic scenarios are loaded from a pre-set BIM model library. The original reference frame model, original experimental pipe pile model, original anchor pile model, and original jack model are then subjected to model refinement processing to obtain a target reference frame model, target experimental pipe pile model, target anchor pile model, and target jack model. Based on the target reference frame model, target experimental pipe pile model, target anchor pile model, and target jack model, the static load test system for pipe piles under compressive load is constructed. Specifically, the original reference frame model described here may include a main beam model, a secondary beam model, and an anchor bar model; the original experimental pipe pile model described here is equipped with a reference beam model and a displacement sensor model; the jack model includes a pressure sensor model; specifically, refer to... Figure 5As shown, in practical applications, target anchor pile models 502 can be installed around the target experimental pipe pile model 501. The secondary beam model 504 and the main beam model 505 are connected via anchor bar models 503 to construct a reference frame model. Under this premise, the combination of anchor piles and the reference frame can provide reaction force to the experimental pipe pile, and the jack model 506 can be used to apply various levels of loads to the experimental pipe pile model. When constructing the system, it is necessary to ensure that the center of the jack model coincides with the axis of the experimental pipe pile. Furthermore, displacement sensors 508 need to be installed on the reference beams 507 around the experimental pipe pile to measure the settlement after each loading stage, ensuring that the displacement sensors are perpendicular to the measurement plane. Pressure sensors 509 are installed on the jacks to monitor the downward load applied by the jacks.

[0090] In one example embodiment, the model refinement process involved in obtaining the target benchmark model, target experimental pipe pile model, target anchor pile model, and target jack model through model refinement processing of the original benchmark model, original experimental pipe pile model, original anchor pile model, and original jack model refers to refining the level of detail of each model. In practical applications, model refinement directly affects the effect of construction simulation. Model precision refinement mainly involves refining the level of detail (LOD) of the model. Furthermore, this level of detail refinement refers to adjusting the level of detail of the model based on the distance between the model and the observer to optimize rendering performance and visual effects. In practical applications, LOD technology improves rendering efficiency and performance by reducing model details far from the observer and reducing the number of polygons. During the level of detail refinement process of the original photovoltaic foundation structure model and the original construction machinery model, automated tools (such as the Mesh Simplification algorithm) can be used to generate LOD models corresponding to the original photovoltaic foundation structure model and the original construction machinery model, and then the corresponding level of refinement processing can be performed according to actual needs.

[0091] Secondly, the settlement and rebound of test pipe piles of different sizes are determined based on the static load test system for pipe piles under compression. Specifically, this can be achieved as follows: any test pipe pile of different sizes is selected as the target pipe pile; different levels of static settlement load are applied to the target pipe pile using the target jack model in the static load test system to obtain the first settlement and first rebound of the target pipe pile under the action of different levels of static settlement load; the process of determining the first settlement and first rebound of the first pipe pile is repeated sequentially to obtain the settlement and rebound of other pipe piles of different sizes excluding the target pipe pile. Specifically, in determining the settlement and rebound of the pipe piles, a slow, sustained load with equal increments can be applied. During actual testing, the load value for each increment can be determined based on the vertical compressive design bearing capacity of the foundation piles. Initially, the load is twice the increment of each increment, followed by equal increments in subsequent increments, with each increment held for a certain period as required by specifications. Furthermore, unloading is also carried out in increments, with each unloading increment being twice the increment of the initial load, and unloading is performed in equal increments. After unloading to zero, the residual settlement at the pile top is measured, and the rebound is determined based on the settlement and the amount of upward movement.

[0092] In step S120, the ultimate compressive bearing capacity of test pipe piles of different sizes is determined based on the settlement amount of the pipe piles, and the rebound rate of test pipe piles of different sizes is determined based on the rebound amount of the pipe piles.

[0093] In this example embodiment, firstly, the ultimate compressive bearing capacity of test pipe piles of different sizes is determined based on the settlement of the pipe piles. Specifically, this can be achieved by: obtaining the pipe pile compressive index curve model associated with the test pipe pile; constructing static settlement load-pipe pile settlement curves for test pipe piles of different sizes based on the pipe pile compressive index curve model and the settlement of the test pipe piles under static settlement loads at different levels; fitting the static settlement load-pipe pile settlement curves for test pipe piles of different sizes to determine the ultimate compressive bearing capacity of test pipe piles of different sizes. Specifically, the pipe pile compressive index curve model described here can be expressed by the following formula (5):

[0094] Q = a(1-e) -ks ); Formula (5)

[0095] Where U is the static settlement load (i.e., the uplift force), δ is the settlement of the pipe pile, a is a parameter greater than zero, and k is the settlement attenuation factor, all in mm. -1Based on the pipe pile compressive strength index curve model and the pipe pile settlement under static settlement loads at different levels, static settlement load-pipe pile settlement curves for test pipe piles of different sizes can be constructed. Specifically, taking three pipe piles of different diameters as an example, the obtained static settlement load-pipe pile settlement curves can be referenced. Figure 6 As shown; in Figure 6 Based on the static settlement load-settlement curve shown, the ultimate compressive bearing capacity of the experimental pipe piles of different sizes can be obtained by fitting and calculating the obtained static settlement load-settlement curve.

[0096] It is important to note that the vertical compressive bearing capacity of a single pile has a significant impact on pile foundation design and engineering costs. Therefore, mastering the ultimate compressive bearing capacity data of the pile is crucial for engineering applications. In actual field tests, twice the characteristic value of the ultimate bearing capacity of a single pile is generally taken as the maximum load value in the test. In practice, the test pipe piles are often not fully loaded to failure, thus the accurate ultimate vertical compressive bearing capacity of a single pile cannot be obtained. Under this premise, by combining field test data with a reliable mathematical model, the ultimate vertical compressive bearing capacity of PHC pipe piles under near-shore conditions can be predicted. This is of great significance for the application of offshore photovoltaic pile foundations. Furthermore, through existing research and analysis, the behavior of the test pipe piles under load can be divided into three stages: under small loads, the pile exhibits an elastic stage; as the load increases, the pile enters an elastoplastic stage; exceeding the ultimate load, the pile loses its bearing capacity and continues to sink. Furthermore, by comparing with existing relevant tests, the exponential curve model can be used to predict the ultimate compressive bearing capacity of experimental pipe piles, which can achieve a relatively accurate prediction result.

[0097] Furthermore, in Figure 6The Qs (static settlement load-pile settlement curve) curves for test pipe piles of different sizes are shown below. For test pile SZ1, when the maximum test load is applied to 360 kN, the cumulative settlement at the pile top is measured to be 37.06 mm, the maximum rebound after unloading is measured to be 30.32 mm, and the residual deformation is 6.74 mm. For test pile SZ2, when the maximum test load is applied to 400 kN, the cumulative settlement at the pile top is measured to be 36.99 mm, the maximum rebound after unloading is measured to be 30.19 mm, and the residual deformation is 6.80 mm. For test pile SZ3, when the maximum test load is applied to 440 kN, the cumulative settlement at the pile top is measured to be 38.10 mm, the maximum rebound after unloading is measured to be 30.74 mm, and the residual deformation is 7.36 mm. During the loading process, the pile settlement increased continuously with the increase of load. Although the displacement increased continuously, the curve did not show a steep drop or obvious inflection point, indicating that none of the three test piles had reached their ultimate bearing capacity. Furthermore, a comparison of the experimental data of the three test piles revealed that, before the load reached 300kN, test pile SZ2 exhibited greater compressive strength than test piles SZ1 and SZ2. However, overall, the curve of test pile SZ3 was flatter, demonstrating better overall compressive strength. This shows that pile diameter has a significant impact on the compressive bearing capacity of marine monopiles, and the larger the pile diameter, the better the compressive bearing capacity.

[0098] Furthermore, in the process of fitting the obtained Qs curve to determine the ultimate compressive bearing capacity of the pipe pile, according to... Figure 7 The exponential curve model prediction results show that the curves for all three piles exhibit a convergence trend, verifying the reliability of the prediction results. The load corresponding to a settlement of 80mm is taken as the ultimate compressive bearing capacity of a single pile. The predicted ultimate compressive bearing capacity for test pile SZ1 is 462.7kN; for test pile SZ2, it is 507.3kN; and for test pile SZ3, it is 578.3kN. The prediction results further verify that the compressive bearing capacity of offshore pile foundations is significantly affected by pile diameter, and the larger the pile diameter, the higher the compressive bearing capacity. Furthermore, under on-site vertical loads, the Qs curves for all three pile diameters show a gradual change, with significant unloading rebound and a clear elastic working shape, indicating good compressive bearing capacity. The curves also show that pile diameter is a crucial factor affecting the compressive bearing capacity of the pile; as the pile diameter increases, the compressive bearing capacity also increases.

[0099] Secondly, the rebound rate of test pipe piles of different sizes is determined based on the rebound amount of the pipe piles. Specifically, this can be achieved as follows: based on the settlement and rebound amount of the pipe piles, the maximum settlement and maximum rebound amount of test pipe piles of different sizes are determined, and the ratio between the maximum settlement and maximum rebound amount is calculated; based on the ratio between the maximum settlement and maximum rebound amount, the rebound rate of test pipe piles of different sizes is determined. Specifically, in practical applications, the rebound rate of the pipe pile can be determined according to the formula: "Rebound rate = Maximum rebound amount / Maximum pull-out amount * 100%". Under this premise, the rebound rate of pile SZ1 can be calculated as: 30.32 / 37.06 * 100% = 81.81%; the rebound rate of pile SZ2 is: 30.19 / 36.99 * 100% = 81.62%; and the rebound rate of pile SZ3 is: 30.74 / 38.10 * 100% = 80.68%. From the rebound rates of the three test piles, it can be seen that the difference in rebound rate during the test is not significant. However, the overall settlement of the 700mm diameter test pile SZ2 is smaller. From an application perspective, test pile SZ2 is more suitable for compressive strength testing. Furthermore, the compressive strength settlement-rebound curves for test pipe piles of different diameters can be referenced. Figure 8 As shown. By Figure 8 The shown curves of settlement and rebound at each compressive stress level indicate that the settlement at each level increases more than the previous level starting from the second loading level, but the rebound at each unloading level tends to stabilize.

[0100] In step S130, the ultimate compressive bearing capacity and rebound rate of the pipe pile are input into the preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear.

[0101] Specifically, the process for determining the predicted service environment that test pipe piles of different sizes can withstand can be achieved as follows: Based on the ultimate compressive bearing capacity, rebound rate, and material parameters of the test pipe piles of different sizes, basic information to be predicted is generated, and context information to be predicted is generated based on preset model prompts; the basic information to be predicted is processed by embedding and mapping based on the first embedding and mapping layer to obtain pipe pile features, and the context information to be predicted is processed by embedding and mapping based on the first embedding and mapping layer to obtain a context flag sequence; the pipe pile features and the context flag sequence are encoded based on the encoding layer to obtain an overall context representation, and the service environment is predicted based on the context flag sequence and the overall context representation using a hybrid expert model to obtain the predicted service environment that the test pipe pile can withstand. Specifically, the preset model prompts described here may be, for example: Your task is to analyze the service environment that experimental pipe piles of different sizes can withstand based on the input information; the first embedding mapping layer described here may include an Embedding embedding mapping layer and a Bert embedding mapping layer; in practical applications, the basic information to be predicted can be embedded and mapped based on the Embedding embedding mapping layer to obtain the pipe pile features, and the context information to be predicted can be embedded and mapped based on the Bert embedding mapping layer to obtain the context flag sequence.

[0102] In an exemplary embodiment, the service environment prediction based on the context flag sequence and the overall context representation, obtained by using a hybrid expert model to predict the service environment that the test pipe pile can bear, can be achieved as follows: Based on the context flag sequence, a gated network model determines the first model weight for performing the environmental prediction task in the weather environment dimension, the second model weight for performing the environmental prediction task in the seawater environment dimension, and the third model weight for performing the environmental prediction task in the seabed soil and rock dimension of the multiple expert neural network models; based on the first model weight, the second model weight, and the third model weight, the weights for performing the environmental prediction task in the weather environment dimension are determined from the multiple expert neural network models. The system comprises a first target network model required for environmental prediction tasks, a second target network model required for environmental prediction tasks in the seawater environment dimension, and a third target network model required for environmental prediction tasks in the seabed soil and rock dimension. The context flag sequence and the overall context representation are input into the first, second, and third target network models, respectively, to obtain the first environmental prediction results in the weather environment dimension, the second environmental prediction results in the seawater environment dimension, and the third environmental prediction results in the seabed soil and rock dimension. Based on the first, second, and third environmental prediction results, the service environment prediction results that the test pipe piles of different sizes can withstand are generated. Specifically, the weather environment dimension mentioned here refers to specific weather conditions, such as wind, frost, rain, and snow; the seawater environment dimension mentioned here may include, but is not limited to, seawater flow velocity, temperature, and depth. Furthermore, after obtaining the first, second, and third environmental prediction results, a weighted summation method can be used to determine the service environment prediction results that the test pipe piles of different sizes can withstand.

[0103] In step S140, the current environmental parameters of the candidate installation area for the pipe pile to be installed are obtained, and based on the service environment prediction results and the current environmental parameters, the corresponding target installation area is matched from the candidate installation area for test pipe piles of different sizes.

[0104] In this example embodiment, firstly, the current environmental parameters are obtained. Specifically, the current environmental parameters described here may include parameters of the weather environment dimension, parameters of the seawater environment dimension, and parameters of the seabed soil and rock dimension. In practical applications, the parameters of the weather environment dimension can be determined based on relevant weather forecast data, the parameters of the seawater environment dimension can be determined based on data collected by relevant sensors, and the parameters of the seabed soil and rock dimension can be determined based on the address data of the area. Secondly, corresponding target installation areas are matched for test pipe piles of different sizes from the candidate installation areas. Specifically, this can be determined as follows: the current environmental parameters and the service environment prediction results are encoded based on a preset word vector embedding model to obtain the current environmental feature vector and the service environment feature vector; the feature similarity between the current environmental feature vector and the service environment feature vector is calculated, and corresponding target installation areas are matched for test pipe piles of different sizes from the candidate installation areas based on the feature similarity. Specifically, the similarity calculation process described here can be calculated from three different dimensions, or it can be combined into a single calculation; this example does not impose any special restrictions on this. Furthermore, when matching target installation areas, the candidate installation area with the highest similarity can be used as the target installation area for experimental pipe piles of different sizes.

[0105] In one exemplary embodiment, the preset word embedding model includes multiple Transformer models and an average pooling layer. The encoding of the current environment parameters based on the preset word embedding model to obtain a current environment feature vector can be achieved as follows: Word embedding is performed on the current environment parameters to obtain word embedding vectors, word embedding matrices, and positional embedding matrices for the current environment parameters; an embedding vector is generated based on the word embedding vectors, word embedding matrices, and positional embedding matrices, and the embedding vector is input into a first Transformer model to generate a first text semantic vector corresponding to the first Transformer model; the first text semantic vector is input into a second Transformer model to generate a second text semantic vector corresponding to the second Transformer model, and the generation process of the second text semantic vector is repeated sequentially to obtain text semantic vectors corresponding to other Transformer models; a first current encoding vector for the current environment parameters is generated based on the text semantic vectors corresponding to each Transformer model and the embedding vector, and the first current encoding vector is input into the average pooling layer to obtain the current environment feature vector. It should be noted that the specific process for determining the service environment feature vector is similar to that for determining the current environment feature vector, and will not be elaborated further here.

[0106] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0107] This disclosure also provides an example embodiment of a device for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems. Specifically, refer to... Figure 9 As shown, the device for predicting the ultimate compressive bearing capacity of the pipe piles for offshore photovoltaic systems may include a pipe pile settlement determination module 910, an ultimate compressive bearing capacity determination module 920, a service environment prediction result determination module 930, and a target installation area determination module 940. Wherein:

[0108] The pipe pile settlement determination module 910 can be used to construct a pipe pile compressive static load test system for offshore photovoltaic scenarios, and determine the pipe pile settlement and rebound of test pipe piles of different sizes based on the pipe pile compressive static load test system.

[0109] The compressive ultimate bearing capacity determination module 920 can be used to determine the compressive ultimate bearing capacity of test pipe piles of different sizes based on the settlement of the pipe pile, and to determine the rebound rate of test pipe piles of different sizes based on the rebound amount of the pipe pile.

[0110] The service environment prediction result determination module 930 can be used to input the ultimate compressive bearing capacity and the rebound rate of the pipe pile into a preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear.

[0111] The target installation area determination module 940 can be used to obtain the current environmental parameters of the candidate installation area for the pipe pile to be installed, and based on the service environment prediction results and the current environmental parameters, match the corresponding target installation area for test pipe piles of different sizes from the candidate installation area.

[0112] In one exemplary embodiment of this disclosure, constructing a static load test system for pipe piles under a marine photovoltaic scenario includes: loading the original reference frame model, the original experimental pipe pile model, the original anchor pile model, and the original jack model required for constructing the static load test system for pipe piles under a marine photovoltaic scenario from a preset BIM model library; performing model refinement processing on the original reference frame model, the original experimental pipe pile model, the original anchor pile model, and the original jack model to obtain the target reference frame model, the target experimental pipe pile model, the target anchor pile model, and the target jack model; and constructing the static load test system for pipe piles based on the target reference frame model, the target experimental pipe pile model, the target anchor pile model, and the target jack model.

[0113] In one exemplary embodiment of this disclosure, determining the settlement and rebound of test pipe piles of different sizes based on a static load test system for pipe piles includes: selecting any test pipe pile of different sizes as a target pipe pile; applying different levels of static settlement load to the target pipe pile using a target jack model in the static load test system to obtain the first settlement and first rebound of the target pipe pile under the action of different levels of static settlement load; and repeating the process of determining the first settlement and first rebound of the first pipe pile in sequence to obtain the settlement and rebound of other pipe piles other than the target pipe pile among the test pipe piles of different sizes.

[0114] In one exemplary embodiment of this disclosure, determining the ultimate compressive bearing capacity of test pipe piles of different sizes based on the settlement of the pipe pile includes: obtaining a pipe pile compressive index curve model associated with the test pipe pile; constructing static settlement load-pipe pile settlement curves for test pipe piles of different sizes based on the pipe pile compressive index curve model and the settlement of the test pipe pile under static settlement loads at different levels; and fitting the static settlement load-pipe pile settlement curves for test pipe piles of different sizes to determine the ultimate compressive bearing capacity of test pipe piles of different sizes.

[0115] In one exemplary embodiment of this disclosure, determining the rebound rate of test pipe piles of different sizes based on the rebound amount includes: determining the maximum settlement and maximum rebound amount of test pipe piles of different sizes based on the settlement and rebound amount of the pipe piles, and calculating the ratio between the maximum settlement and the maximum rebound amount; and determining the rebound rate of test pipe piles of different sizes based on the ratio between the maximum settlement and the maximum rebound amount.

[0116] In one exemplary embodiment of this disclosure, the preset service environment prediction model includes a first embedding mapping layer, an encoding layer, and a hybrid expert model. The process involves inputting the ultimate compressive bearing capacity and rebound rate of the pipe pile into the preset service environment prediction model to obtain the service environment prediction results for test pipe piles of different sizes. This includes: generating basic information to be predicted based on the ultimate compressive bearing capacity, rebound rate, and material parameters of the test pipe piles of different sizes; generating context information to be predicted based on preset model prompts; performing embedding mapping processing on the basic information to be predicted based on the first embedding mapping layer to obtain pipe pile features; performing embedding mapping processing on the context information to be predicted based on the first embedding mapping layer to obtain a context flag sequence; encoding the pipe pile features and context flag sequence based on the encoding layer to obtain a context overall representation; and performing service environment prediction on the context flag sequence and context overall representation based on the hybrid expert model to obtain the service environment prediction results for the test pipe piles.

[0117] In one exemplary embodiment of this disclosure, the hybrid expert model includes a gated network model and multiple expert neural network models; wherein, based on the hybrid expert model, service environment prediction is performed on the context flag sequence and the overall context representation to obtain the service environment prediction result that the test pipe pile can bear, including: determining, based on the gated network model and the context flag sequence, a first model weight for performing an environmental prediction task in the weather environment dimension, a second model weight for performing an environmental prediction task in the seawater environment dimension, and a third model weight for performing an environmental prediction task in the seabed soil and rock dimension of the multiple expert neural network models; based on the first model weight, the second model weight, and the third model weight, from the multiple expert neural network models... The system determines the first target network model required for performing environmental prediction tasks in the weather environment dimension, the second target network model required for performing environmental prediction tasks in the seawater environment dimension, and the third target network model required for performing environmental prediction tasks in the seabed rock and soil dimension. The context flag sequence and the overall context representation are input into the first target network model, the second target network model, and the third target network model, respectively, to obtain the first environmental prediction results in the weather environment dimension, the second environmental prediction results in the seawater environment dimension, and the third environmental prediction results in the seabed rock and soil dimension. Based on the first environmental prediction results, the second environmental prediction results, and the third environmental prediction results, the service environment prediction results that the test pipe piles of different sizes can bear are generated.

[0118] In one exemplary embodiment of this disclosure, matching target installation areas for test pipe piles of different sizes from candidate installation areas based on the service environment prediction results and current environmental parameters includes: encoding the current environmental parameters and service environment prediction results based on a preset word vector embedding model to obtain current environmental feature vectors and service environment feature vectors; calculating the feature similarity between the current environmental feature vectors and service environment feature vectors; and matching target installation areas for test pipe piles of different sizes from candidate installation areas based on the feature similarity.

[0119] In an exemplary embodiment of this disclosure, the preset word embedding model includes multiple Transformer models and an average pooling layer; wherein, encoding the current environment parameters based on the preset word embedding model to obtain a current environment feature vector includes: embedding words into the current environment parameters to obtain word embedding vectors, word embedding matrices, and position embedding matrices of the current environment parameters; generating embedding vectors based on the word embedding vectors, word embedding matrices, and position embedding matrices, and inputting the embedding vectors into a first Transformer model to generate a first text semantic vector corresponding to the first Transformer model; inputting the first text semantic vector into a second Transformer model to generate a second text semantic vector corresponding to the second Transformer model, and repeating the generation process of the second text semantic vectors sequentially to obtain text semantic vectors corresponding to other Transformer models; generating a first current encoding vector for the current environment parameters based on the text semantic vectors corresponding to each Transformer model and the embedding vectors, and inputting the first current encoding vector into the average pooling layer to obtain the current environment feature vector.

[0120] The specific details of each module in the aforementioned prediction device for the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems have been described in detail in the corresponding prediction method for the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems, so they will not be repeated here.

[0121] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0122] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0123] In exemplary embodiments of this disclosure, an electronic device capable of implementing the above-described methods is also provided. Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0124] The following reference Figure 10 To describe an electronic device 1000 according to such an embodiment of the present disclosure. Figure 10 The electronic device 1000 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0125] like Figure 10 As shown, the electronic device 1000 is manifested in the form of a general-purpose computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processing unit 1010, at least one storage unit 1020, a bus 1030 connecting different system components (including storage unit 1020 and processing unit 1010), and a display unit 1040.

[0126] The storage unit stores program code that can be executed by the processing unit 1010, causing the processing unit 1010 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 1010 can perform actions such as... Figure 1Step S110: Construct a static load test system for pipe piles under offshore photovoltaic scenarios, and determine the settlement and rebound of test pipe piles of different sizes based on the static load test system; Step S120: Determine the ultimate compressive bearing capacity of test pipe piles of different sizes based on the settlement, and determine the rebound rate of test pipe piles of different sizes based on the rebound; Step S130: Input the ultimate compressive bearing capacity and rebound rate of pipe piles into a preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear; Step S140: Obtain the current environmental parameters of the candidate installation area for pipe pile installation, and match the corresponding target installation area for test pipe piles of different sizes from the candidate installation area based on the service environment prediction results and the current environmental parameters.

[0127] Storage unit 1020 may include readable media in the form of volatile storage units, such as random access memory (RAM) 10201 and / or cache memory 10202, and may further include read-only memory (ROM) 10203.

[0128] Storage unit 1020 may also include a program / utility 10204 having a set (at least one) program module 10205, such program module 10205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0129] Bus 1030 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the multiple bus structures.

[0130] Electronic device 1000 can also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 1000, and / or any device that enables electronic device 1000 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1050. Furthermore, electronic device 1000 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1060. As shown, network adapter 1060 communicates with other modules of electronic device 1000 via bus 1030. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0131] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0132] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0133] The program product for implementing the above-described method according to embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0134] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0135] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0136] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0137] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0138] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0139] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention described herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not invented by this disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems, characterized in that, include: A static load test system for pipe piles under offshore photovoltaic scenarios was constructed, and the settlement and rebound of pipe piles of different sizes were determined based on the static load test system. The ultimate compressive bearing capacity of test pipe piles of different sizes is determined based on the settlement amount of the pipe piles, and the rebound rate of test pipe piles of different sizes is determined based on the rebound amount of the pipe piles. The ultimate compressive bearing capacity and rebound rate of the pipe pile are input into a preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear. The current environmental parameters of the candidate installation area for the pipe pile to be installed are obtained, and based on the service environment prediction results and the current environmental parameters, the corresponding target installation area is matched from the candidate installation area for test pipe piles of different sizes.

2. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 1, characterized in that, Constructing a static load test system for pipe piles in an offshore photovoltaic scenario, including: Load the original reference frame model, original experimental pipe pile model, original anchor pile model, and original jack model required for constructing the static load test system for pipe piles in the offshore photovoltaic scenario from the preset BIM model library. The original reference frame model, original experimental pipe pile model, original anchor pile model, and original jack model are subjected to model refinement processing to obtain the target reference frame model, target experimental pipe pile model, target anchor pile model, and target jack model. Based on the target reference frame model, target experimental pipe pile model, target anchor pile model, and target jack model, the pipe pile static load test system is constructed.

3. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 2, characterized in that, The settlement and rebound of test pipe piles of different sizes were determined based on the static load test system for pipe piles, including: Select any test pipe pile of different sizes as the target pipe pile; The target jack model in the static load test system for pipe pile compression is used to apply different levels of static sinking load to the target pipe pile in order to obtain the first pipe pile sinking amount and the first pipe pile rebound amount under the action of different levels of static sinking load. The process of determining the settlement and rebound of the first pipe pile is repeated sequentially to obtain the settlement and rebound of other pipe piles (excluding the target pipe pile) among the test pipe piles of different sizes.

4. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 1, characterized in that, The ultimate compressive bearing capacity of test pipe piles of different sizes is determined based on the settlement of the pipe piles, including: Obtain the pipe pile compressive strength index curve model associated with the test pipe pile; Based on the pipe pile compressive strength index curve model and the pipe pile settlement under different levels of static settlement load, static settlement load-pipe pile settlement curves for test pipe piles of different sizes are constructed. The static settlement load-settlement curves of test pipe piles of different sizes were fitted to determine the ultimate compressive bearing capacity of test pipe piles of different sizes.

5. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 1, characterized in that, The rebound rate of test pipe piles of different sizes is determined based on the rebound amount, including: Based on the settlement and rebound of the pipe piles, the maximum settlement and rebound of test pipe piles of different sizes are determined, and the ratio between the maximum settlement and the maximum rebound is calculated. The rebound rate of test pipe piles of different sizes is determined based on the ratio between the maximum settlement and the maximum rebound.

6. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 1, characterized in that, The preset service environment prediction model includes a first embedding mapping layer, an encoding layer, and a hybrid expert model; The ultimate compressive bearing capacity and rebound rate of the pipe piles are input into a pre-set service environment prediction model to obtain the predicted service environment conditions that test pipe piles of different sizes can withstand, including: Based on the ultimate compressive bearing capacity, rebound rate, and material parameters of test pipe piles of different sizes, the basic information to be predicted is generated, and the context information to be predicted is generated based on the preset model prompts. The first embedding mapping layer is used to perform embedding mapping processing on the basic information to be predicted to obtain the pipe pile features, and the first embedding mapping layer is used to perform embedding mapping processing on the context information to be predicted to obtain the context flag sequence. The features of the pipe pile and the context flag sequence are encoded based on the coding layer to obtain the overall context representation. Then, the service environment is predicted based on the context flag sequence and the overall context representation using a hybrid expert model to obtain the predicted service environment that the test pipe pile can bear.

7. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 6, characterized in that, Hybrid expert models include gated network models and multiple expert neural network models; Specifically, the service environment prediction is performed based on the context flag sequence and the overall context representation using a hybrid expert model, resulting in a predicted service environment that the test pipe pile can withstand, including: Based on the gating network model and the context flag sequence, the first model weights of the multiple expert neural network models for performing environmental prediction tasks in the weather environment dimension, the second model weights for performing environmental prediction tasks in the marine environment dimension, and the third model weights for performing environmental prediction tasks in the seabed rock and soil dimension are determined. Based on the first model weight, the second model weight, and the third model weight, the first target network model required to perform the environmental prediction task in the weather environment dimension, the second target network model required to perform the environmental prediction task in the seawater environment dimension, and the third target network model required to perform the environmental prediction task in the seabed rock and soil dimension are determined from the multiple expert neural network models. The context flag sequence and the overall context representation are input into the first target network model, the second target network model and the third target network model respectively to obtain the first environmental prediction result in the weather environment dimension, the second environmental prediction result in the seawater environment dimension and the third environmental prediction result in the seabed rock and soil dimension. Based on the first environmental prediction results, the second environmental prediction results, and the third environmental prediction results, the service environment prediction results that the test pipe piles of different sizes can withstand are generated.

8. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 1, characterized in that, Based on the service environment prediction results and current environmental parameters, target installation areas are matched for test pipe piles of different sizes from the candidate installation areas, including: The current environmental parameters and service environment prediction results are encoded based on a preset word vector embedding model to obtain the current environmental feature vector and the service environment feature vector. Calculate the feature similarity between the current environment feature vector and the service environment feature vector, and match the corresponding target installation area for test pipe piles of different sizes from the candidate installation areas based on the feature similarity.

9. The method for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems according to claim 8, characterized in that, The preset word vector embedding model includes multiple Transformer models and an average pooling layer; wherein, the current environment parameters are encoded based on the preset word vector embedding model to obtain the current environment feature vector, including: Word embedding is performed on the current environment parameters to obtain the word embedding vector, word embedding matrix, and position embedding matrix of the current environment parameters; Based on the character embedding vector, character embedding matrix, and position embedding matrix, an embedding vector is generated, and the embedding vector is input into the first Transformer model to generate the first text semantic vector corresponding to the first Transformer model. The first text semantic vector is input into the second Transformer model to generate the second text semantic vector corresponding to the second Transformer model. The process of generating the second text semantic vector is repeated in turn to obtain the text semantic vectors corresponding to other Transformer models. The first current encoding vector of the current environment parameters is generated based on the text semantic vector and embedding vector corresponding to each Transformer model, and the first current encoding vector is input into the average pooling layer to obtain the current environment feature vector.

10. A device for predicting the ultimate compressive bearing capacity of pipe piles for offshore photovoltaic systems, characterized in that, include: The pipe pile settlement determination module is used to construct a pipe pile compressive static load test system for offshore photovoltaic scenarios, and to determine the pipe pile settlement and rebound of test pipe piles of different sizes based on the pipe pile compressive static load test system. The compressive ultimate bearing capacity determination module is used to determine the compressive ultimate bearing capacity of test pipe piles of different sizes based on the settlement of the pipe pile, and to determine the rebound rate of test pipe piles of different sizes based on the rebound amount of the pipe pile. The service environment prediction result determination module is used to input the ultimate compressive bearing capacity and rebound rate of the pipe pile into the preset service environment prediction model to obtain the service environment prediction results that test pipe piles of different sizes can bear. The target installation area determination module is used to obtain the current environmental parameters of the candidate installation areas for the pipe piles to be installed, and based on the service environment prediction results and the current environmental parameters, to match the corresponding target installation areas for test pipe piles of different sizes from the candidate installation areas.

Images