Pipe pile determination method and device in offshore photovoltaic scene, electronic equipment and medium

Abstract

This disclosure provides a method, apparatus, electronic device, and computer-readable storage medium for determining pipe piles in offshore photovoltaic (PV) scenarios, belonging to the field of offshore PV technology. The method includes: acquiring multi-source data of a target sea area in the current offshore PV business scenario; extracting a first type of key data and a second type of key data from the environmental characteristic data, economic characteristic data, and construction characteristic data; processing the first type of key data through a first network layer to obtain first intermediate data, and processing the second type of key data through a second network layer to obtain second intermediate data; processing the first intermediate data and the second intermediate data through a third network layer to obtain target intermediate data; and determining the target pipe pile type for the target sea area in the current offshore PV business scenario based on the target intermediate data. This disclosure can quickly and accurately determine the target pipe pile type suitable for the target sea area.

Description

Technical Field

[0001] This disclosure relates to the field of offshore photovoltaic operation technology, and in particular to a method for determining pipe piles in an offshore photovoltaic scenario, a device for determining pipe piles in an offshore photovoltaic scenario, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Offshore photovoltaics (PV) is a new clean energy development method that utilizes marine space to install photovoltaic panels and convert solar energy into electricity. This technology, by installing photovoltaic panels at sea and directly converting solar radiation into electricity, helps reduce dependence on fossil fuels, reduce greenhouse gas emissions, and promote the green transformation of the global energy structure. The installation of offshore photovoltaic panels requires first driving piles into the sea to fix the pipe piles in place, and then hoisting the photovoltaic panels into the corresponding positions on the pipe piles. However, due to the variety of pipe pile types, using different types of pipe piles in the sea will have different impacts on the installation of photovoltaic panels and the subsequent progress of photovoltaic projects. Existing technologies typically use a trial-and-error approach or select the pipe pile type based on experience. However, this approach not only cannot guarantee the effectiveness of the selected pipe piles but also incurs significant trial-and-error costs.

[0003] Therefore, how to quickly and accurately determine the appropriate pipe piles for the marine environment is a problem that needs to be solved by existing technologies.

[0004] It should be noted that the information disclosed 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] This disclosure provides a method for determining pipe piles in offshore photovoltaic scenarios, a device for determining pipe piles in offshore photovoltaic scenarios, an electronic device, and a computer-readable storage medium, thereby at least partially solving the problem that existing technologies cannot quickly and accurately determine the appropriate type of pipe pile in offshore photovoltaic scenarios.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a method for determining pipe piles in an offshore photovoltaic (PV) scenario is provided, comprising: acquiring multi-source data of a target sea area in the current offshore PV business scenario; the multi-source data including at least environmental characteristic data, economic characteristic data, and construction characteristic data; extracting a first type of key data and a second type of key data from the environmental characteristic data, economic characteristic data, and construction characteristic data; processing the first type of key data through a first network layer to obtain first intermediate data, and processing the second type of key data through a second network layer to obtain second intermediate data; processing the first intermediate data and the second intermediate data through a third network layer to obtain target intermediate data; and determining the target pipe pile type in the target sea area of ​​the current offshore PV business scenario based on the target intermediate data.

[0008] In an exemplary embodiment of this disclosure, the step of extracting a first type of key data and a second type of key data from the environmental feature data, economic feature data, and construction feature data includes: extracting soil layer distribution data of the target sea area from the environmental feature data, and determining a geological profile image of the target sea area based on the soil layer distribution data; extracting marine parameter index data of the target sea area from the environmental feature data, and determining a marine parameter heat map based on the marine parameter index data; the marine parameter index data includes at least sea depth data and wave height data; using the geological profile image of the target sea area and the marine parameter heat map as the first type of key data; and determining the second type of key data based on the economic feature data and construction feature data.

[0009] In one exemplary embodiment of this disclosure, determining the second type of key data based on the economic characteristic data and construction characteristic data includes: extracting transportation cost data from the economic characteristic data and calculating a first correlation data between the transportation cost data and different time series; extracting piling resistance data from the construction characteristic data and calculating a second correlation data between the piling resistance data and different time series; and determining the second type of key data based on the first correlation data and the second correlation data.

[0010] In one exemplary embodiment of this disclosure, determining the second type of key data based on the first correlation data and the second correlation data includes: performing an association calculation between the first correlation data and the second correlation data, and using the calculation result as the second type of key data.

[0011] In one exemplary embodiment of this disclosure, the method further includes: generating a simulation image under a preset geological environment based on the geological profile image; the step of using the geological profile image of the target sea area and the sea area parameter heat map as the first type of key data includes: using the geological profile image of the target sea area, the simulation image under the preset geological environment, and the sea area parameter heat map as the first type of key data.

[0012] In an exemplary embodiment of this disclosure, the step of processing the first intermediate data and the second intermediate data through a third network layer to obtain target intermediate data includes: processing the first intermediate data and the second intermediate data through a third network layer to obtain evaluation index data for the target sea area; the evaluation index data includes one or more of bearing capacity index data, cost index data, and construction cycle index data; the step of determining the target pipe pile type in the target sea area in the current offshore photovoltaic business scenario based on the target intermediate data includes: processing the evaluation index data through a pre-trained pipe pile prediction network to output a pipe pile type probability distribution; and determining the target pipe pile type for the target sea area based on the pipe pile type probability distribution.

[0013] In one exemplary embodiment of this disclosure, the method further includes: collecting sensing data through IoT sensors configured in the current offshore photovoltaic business scenario; and correcting the environmental feature data, the economic feature data, or the construction feature data in real time based on the sensing data.

[0014] According to one aspect of this disclosure, a device for determining pipe piles in an offshore photovoltaic scenario is provided, comprising: a multi-source data acquisition module for acquiring multi-source data of a target sea area in the current offshore photovoltaic business scenario; the multi-source data includes at least environmental characteristic data, economic characteristic data, and construction characteristic data; a key data extraction module for extracting a first type of key data and a second type of key data from the environmental characteristic data, economic characteristic data, and construction characteristic data; an intermediate data acquisition module for processing the first type of key data through a first network layer to obtain first intermediate data, and processing the second type of key data through a second network layer to obtain second intermediate data; an intermediate data processing module for processing the first intermediate data and the second intermediate data through a third network layer to obtain target intermediate data; and a pipe pile type determination module for determining the target pipe pile type of the target sea area in the current offshore photovoltaic business scenario based on the target intermediate data.

[0015] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method described in any of the preceding methods by executing the executable instructions.

[0016] According to one aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the preceding claims.

[0017] The exemplary embodiments disclosed herein have the following beneficial effects:

[0018] Acquire multi-source data for the target sea area in the current offshore photovoltaic business scenario; the multi-source data includes at least environmental characteristic data, economic characteristic data, and construction characteristic data; extract a first type of key data and a second type of key data from the environmental characteristic data, economic characteristic data, and construction characteristic data; process the first type of key data through a first network layer to obtain first intermediate data, and process the second type of key data through a second network layer to obtain second intermediate data; process the first intermediate data and the second intermediate data through a third network layer to obtain target intermediate data; determine the target pipe pile type in the target sea area of ​​the current offshore photovoltaic business scenario based on the target intermediate data. On the one hand, this exemplary embodiment proposes a novel method for determining pipe piles. Compared to the prior art's method of determining pipe piles through trial and error or human experience, this exemplary embodiment can quickly predict accurate and effective target pipe pile types based on multi-source data of the target sea area, greatly saving trial and error costs and manpower costs, while ensuring the accuracy of pipe pile type determination. On the other hand, this exemplary embodiment considers multi-source data of the target sea area, processes different key data through different network layers, and determines target intermediate data based on the obtained intermediate data, thereby determining the target pipe pile type of the target sea area. This approach, starting from multi-dimensional data and performing data processing and fusion through multi-level processing steps to finally determine the target pipe pile type, can further ensure the relevance and applicability of the determined target pipe pile type to the target sea area.

[0019] 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

[0020] 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.

[0021] Figure 1 This schematic diagram illustrates a system architecture diagram of a pipe pile determination method in an offshore photovoltaic scenario according to an exemplary embodiment of the present invention;

[0022] Figure 2 This schematically illustrates a flowchart of a method for determining pipe piles in an offshore photovoltaic scenario according to an exemplary embodiment of the present invention;

[0023] Figure 3 This schematically illustrates a sub-flowchart of a method for determining pipe piles in an offshore photovoltaic scenario according to an exemplary embodiment of the present invention;

[0024] Figure 4 This schematic diagram illustrates the structural block diagram of a pipe pile determining device in an offshore photovoltaic scenario according to an exemplary embodiment of the present invention;

[0025] Figure 5 An electronic device for implementing the above method is illustrated in this exemplary embodiment. Detailed Implementation

[0026] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0027] An exemplary embodiment of this disclosure first provides a method for determining pipe piles in an offshore photovoltaic (PV) scenario, applicable to offshore PV business scenarios. The application scenario of this method can be: determining pipe piles for use in the current offshore PV business scenario within an offshore PV project.

[0028] Figure 1 A schematic diagram of a system architecture for the operating environment of this exemplary embodiment is shown, with reference to... Figure 1 As shown, the system 100 may include a server 110 and a target sea area 120. The server 110 obtains multi-source data from the target sea area 120 and processes it to determine the target pipe pile type in the target sea area 120. After determining the target pipe pile type, it can return the data to the user terminal.

[0029] It should be understood that Figure 1 The data for each device shown are merely illustrative. Depending on actual needs, any number of servers can be configured; for example, the servers can be a server cluster consisting of multiple servers. Based on the above description, the method in this exemplary embodiment can be applied to… Figure 1 On server 110 shown.

[0030] The following is in conjunction with the appendix Figure 2 The exemplary embodiments will be further described as follows: Figure 2 As shown, the method for determining the pipe piles in an offshore photovoltaic scenario may include the following steps S210 to S250:

[0031] Step S210: Obtain multi-source data of the target sea area in the current offshore photovoltaic business scenario; the multi-source data includes at least environmental characteristic data, economic characteristic data, and construction characteristic data.

[0032] The target sea area refers to the sea area where operations such as piling, hoisting, or installing photovoltaic panels are required in offshore photovoltaic business scenarios. Multi-source data refers to data related to the target sea area from different dimensions, which can include at least environmental characteristic data, economic characteristic data, and construction characteristic data. Environmental characteristic data is data related to the environment of the target sea area, such as sea depth, wave height, wind speed, soil layer distribution, and geological structure data. Economic characteristic data refers to economic parameters that may be involved in operations in the target sea area, such as material costs of different pipe materials, transportation costs, or equipment rental / usage fees. Construction characteristic data refers to corresponding operational parameter data when operations are carried out in the target sea area, such as piling equipment parameters, piling resistance records, and construction window data.

[0033] This exemplary embodiment can be configured with one or more sensors in the current offshore photovoltaic business scenario to acquire multi-source data of the target sea area by collecting sensor data, or it can be obtained by technicians through on-site data survey in the current offshore photovoltaic business scenario. This disclosure does not make any specific limitations in this regard.

[0034] Step S220: Extract the first type of key data and the second type of key data from environmental characteristic data, economic characteristic data and construction characteristic data.

[0035] This exemplary embodiment can extract a first type of key data and a second type of key data from environmental feature data, economic feature data, and construction feature data. Specifically, it can extract data from environmental feature data, economic feature data, and construction feature data respectively, and divide the extracted data into a first type of key data and a second type of key data; or it can extract the first type of key data from environmental feature data and extract the second type of key data from economic feature data and construction feature data, etc.

[0036] In this exemplary embodiment, the first type of key data may be image data, and the second type of key data may be time-related data. Therefore, image-related data can be extracted from environmental feature data, and image data can be generated based on the extracted data as the first type of key data. Time-affected data can be extracted from economic feature data and construction feature data, and time-series data can be generated as the second type of key data.

[0037] Step S230: Process the first type of key data through the first network layer to obtain the first intermediate data, and process the second type of key data through the second network layer to obtain the second intermediate data.

[0038] The first network layer can be a CNN (Convolutional Neural Network) layer, which processes the first type of key data to obtain first intermediate data. This first intermediate data can be the output of the first network layer. For example, image data related to environmental features can be input into the CNN layer for processing to obtain intermediate feature data. The second network layer can be an LSTM (Long Short-Term Memory) layer, which processes the second type of key data to obtain second intermediate data. This second intermediate data can be the output of the second network layer. For example, time-series data related to economic features or construction features can be input into the LSTM layer for processing to obtain intermediate feature data.

[0039] Step S240: The first intermediate data and the second intermediate data are processed through the third network layer to obtain the target intermediate data.

[0040] The third network layer can be a network layer used to fuse the first intermediate data and the second intermediate data. For example, the third network layer can be a Transformer (embedding) layer. In this exemplary embodiment, the first and second intermediate data can be fused using the third network layer to obtain target intermediate data. For example, the first and second intermediate data can be in vector or matrix form. The third network layer can merge or concatenate the first and second intermediate data to obtain matrix data including the first and second intermediate data, i.e., the target intermediate data. In this exemplary embodiment, the target intermediate data can be comprehensive feature data that fuses image features and temporal features. Based on this target intermediate data, the prediction and selection of pipe pile types can be performed more comprehensively and accurately.

[0041] Step S250: Determine the target pipe pile type in the target sea area of ​​the current offshore photovoltaic business scenario based on the target intermediate data.

[0042] In offshore photovoltaic business scenarios, various types of pipe piles can be included, such as high-strength prestressed concrete pipe piles, bamboo-joint piles, steel strand piles, steel pipe piles, and precast high-strength concrete thin-walled steel pipe columns. Different pipe piles have different effective prestress, strength grade, bearing capacity, and adaptability. Selecting pipe piles suitable for the marine environment can ensure the stability of photovoltaic panel installation and ensure that material costs are fully utilized without being wasted.

[0043] After determining the target intermediate data, this exemplary embodiment can determine the target pipe pile type for the target sea area in the current offshore photovoltaic business scenario based on the target intermediate data. For example, a pre-trained neural network model can be used to process the target intermediate data, input the prediction probability of different pipe pile types, and determine the pipe pile type with the highest prediction probability as the target pipe pile type; or the pipe pile type classification result can be directly output to give the target pipe pile type suitable for the current target sea area.

[0044] Based on the above description, in this exemplary embodiment, multi-source data of the target sea area in the current offshore photovoltaic business scenario is acquired; the multi-source data includes at least environmental characteristic data, economic characteristic data, and construction characteristic data; a first type of key data and a second type of key data are extracted from the environmental characteristic data, economic characteristic data, and construction characteristic data; the first type of key data is processed through a first network layer to obtain first intermediate data, and the second type of key data is processed through a second network layer to obtain second intermediate data; the first intermediate data and the second intermediate data are processed through a third network layer to obtain target intermediate data; and the target pile type in the target sea area of ​​the current offshore photovoltaic business scenario is determined based on the target intermediate data. On the one hand, this exemplary embodiment proposes a novel method for determining pipe piles. Compared to the prior art's method of determining pipe piles through trial and error or human experience, this exemplary embodiment can quickly predict accurate and effective target pipe pile types based on multi-source data of the target sea area, greatly saving trial and error costs and manpower costs, while ensuring the accuracy of pipe pile type determination. On the other hand, this exemplary embodiment considers multi-source data of the target sea area, processes different key data through different network layers, and determines target intermediate data based on the obtained intermediate data, thereby determining the target pipe pile type of the target sea area. This approach, starting from multi-dimensional data and performing data processing and fusion through multi-level processing steps to finally determine the target pipe pile type, can further ensure the relevance and applicability of the determined target pipe pile type to the target sea area.

[0045] In one exemplary embodiment, such as Figure 3 As shown, the extraction of the first and second types of key data from environmental characteristic data, economic characteristic data, and construction characteristic data can include the following steps:

[0046] Step S310: Extract the soil layer distribution data of the target sea area from the environmental characteristic data, and determine the geological profile image of the target sea area according to the soil layer distribution data;

[0047] Step S320: Extract the sea area parameter index data of the target sea area from the environmental characteristic data, and determine the sea area parameter heat map according to the sea area parameter index data; the sea area parameter index data at least includes sea area depth data and wave height data;

[0048] Step S330: Take the geological profile image and the sea area parameter heat map of the target sea area as the first type of key data;

[0049] Step S340: Determine the second type of key data according to the economic characteristic data and the construction characteristic data.

[0050] In this exemplary embodiment, the environmental characteristic data may include various data, such as soil layer distribution data, sea area depth data, wave height data, and so on.

[0051] In this exemplary embodiment, the soil layer distribution data can be extracted from the environmental characteristic data first. The soil layer distribution data refers to the data used to reflect the spatial distribution of the soil layer. In this exemplary embodiment, the SPT (standard penetration test) value can be determined by conducting a standard penetration test on the target sea area, and the SPT value is used as the soil layer distribution data. For example, the SPT values of multiple drilling points in the target sea area can be obtained. According to actual needs, the collected SPT values can also be subjected to outlier rejection, or spatial interpolation can be performed on the discrete SPT values to generate continuous soil layer distribution data, etc. After determining the soil layer distribution data, a geological modeling tool can be used to map the layer distribution data into a layered geological model. For example, when SPT ≤ 4, it is determined as a silt layer and represented by blue; when 4 < SPT ≤ 15, it is determined as a sand layer and represented by yellow; when SPT > 15, it is determined as a clay layer or a rock layer and represented by gray, etc. Based on the layered geological model, the geological profile image, such as a horizontal sectional view, can be further determined. According to actual needs, the dividing lines and depth information of different soil layers can also be marked in the image.

[0052] This exemplary embodiment can also extract sea area depth data and wave height data from environmental feature data. For example, the target sea area can be divided into grids of a preset size (e.g., 100*100). Then, the corresponding sea area depth data and wave height data can be obtained from each grid. If there are missing areas, interpolation can be performed using neighboring data to obtain the relevant data. Then, a sea area parameter heatmap can be determined based on the sea area parameter index data. For example, using algorithm tools, the grid distribution of the target sea area and the corresponding grid data can be loaded to generate depth heatmaps and wave height heatmaps respectively. Furthermore, a sea area parameter heatmap can be generated based on the depth heatmap and wave height heatmap. For example, the depth heatmap and wave height heatmap can be directly used as the sea area parameter heatmap; or a composite heatmap can be generated by overlaying the depth heatmap and wave height heatmap. As needed, the composite heatmap can also add the boundary and key coordinate point information of the target sea area. The regional points in the composite heatmap can correspond to the sea area depth data and wave height data of the corresponding region. Then, the composite heatmap can be used as the sea area parameter heatmap, etc.

[0053] Finally, the geological profile image and marine parameter heat map of the target sea area are used as the first type of key data. For example, in this exemplary embodiment, the geological profile image and marine parameter heat map can be integrated into a multi-channel image tensor. For example, channel 1 can be a geological profile grayscale image to reflect the distribution of soil layers, channel 2 can be a depth heat map, channel 3 can be a wave height heat map, etc. As needed, information such as coordinate range, scale bar or data acquisition timestamp can also be added.

[0054] In addition, considering that economic characteristic data and construction characteristic data may be affected by time and may have significant differences at different times, this exemplary embodiment can also determine a second type of key data based on economic characteristic data and construction characteristic data.

[0055] Specifically, in an exemplary embodiment, determining the second type of key data based on economic characteristic data and construction characteristic data may include:

[0056] Transportation cost data is extracted from economic characteristic data, and the first correlation data of transportation cost data between different time series is calculated.

[0057] Piling resistance data is extracted from construction characteristic data, and the second correlation data of piling resistance data between different time series are calculated.

[0058] Based on the first and second correlation data, the second type of key data is determined.

[0059] When determining the second type of key data, transportation cost data can be extracted from economic characteristic data, and the first correlation data between different time series of transportation cost data can be calculated. For example, multiple transportation cost time series data can be constructed based on transportation cost data of different time series, and then the first correlation data between multiple transportation cost time series data can be calculated. Specifically, the transportation cost time series data can be calculated through a multi-head attention mechanism to obtain the first correlation data between different time series of transportation cost data.

[0060] Considering that the pile driving resistance may change with the pile driving depth, this exemplary embodiment can also extract the pile driving resistance data from the construction feature data when determining the second type of key data. For example, multiple pile driving resistance time series data can be constructed based on pile driving resistance data of different time series. Then, based on the multiple pile driving resistance time series data, the second correlation data between different time series of pile driving resistance data can be calculated.

[0061] After obtaining the first and second correlation data, the second type of key data can be obtained by associating the first and second correlation data.

[0062] In an exemplary embodiment, determining the second type of key data based on the first correlation data and the second correlation data may include:

[0063] The first correlation data and the second correlation data are correlated and calculated, and the calculation result is used as the second type of key data.

[0064] This exemplary embodiment can associate the first and second correlation data through a spatiotemporal attention association module, and use the calculation result as the second type of key data. For example, the second type of key data, Attention, can be determined in the following way. total :

[0065] Attention total =[Attention1,Attention2] T

[0066] Here, Attention1 represents the first relevant data and Attention2 represents the second relevant data.

[0067] In an exemplary embodiment, the method for determining the pipe piles in the above-described offshore photovoltaic scenario may further include:

[0068] Based on geological profile images, simulated images under a preset geological environment are generated;

[0069] The aforementioned geological profile images and marine parameter heat maps of the target sea area, used as the first type of key data, may include:

[0070] Geological profile images of the target sea area, simulation images under the preset geological environment, and sea area parameter heat maps are used as the first type of key data.

[0071] To ensure the accuracy of determining the type of pipe pile, this exemplary embodiment can perform data augmentation based on geological profile images to generate simulated images under a preset geological environment, such as generating geological profile images of seabed scour patterns under a preset level (e.g., the strongest level) typhoon load. Then, the first type of key data is determined based on the existing geological profile images, the data-augmented simulated images under the preset geological environment, and the marine parameter thermal images.

[0072] In an exemplary embodiment, the above-described processing of the first intermediate data and the second intermediate data through a third network layer to obtain the target intermediate data may include:

[0073] The first and second intermediate data are processed by the third network layer to obtain the evaluation index data of the target sea area; the evaluation index data includes one or more of the following: carrying capacity index data, cost index data, and construction period index data.

[0074] Based on the target intermediate data, determine the target pipe pile type for the target sea area in the current offshore photovoltaic business scenario, including:

[0075] The evaluation index data is processed by a pre-trained pipe pile prediction network to output the probability distribution of pipe pile type.

[0076] The target pipe pile type for the target sea area is determined based on the probability distribution of pipe pile type.

[0077] This exemplary embodiment can process the first and second intermediate data through a third network layer. For example, it can concatenate the two types of data and input them into a fully connected layer for feature fusion, then output evaluation index data for the target sea area. This evaluation index data can be index data used to evaluate the state of the target sea area. For example, this exemplary embodiment can process the fused feature data of the first and second intermediate data to obtain one or more of the following: bearing capacity index data, cost index data, and construction cycle index data for the target sea area. The bearing capacity index data can reflect the target sea area's ability to support pipe piles, such as the maximum number of pipe piles it can accommodate or the pipe pile density. The cost index data can be the cost data for pile driving operations in the target sea area. The construction cycle index data can be the construction cycle data for pile driving operations in the target sea area, such as the construction cycle of a preset number of pipe piles or the average construction cycle of each pipe pile.

[0078] Then, the evaluation index data of the target sea area can be input into the pre-trained pipe pile prediction network for processing, and the probability distribution of pipe pile type can be output. For example, the bearing capacity index data, cost index data, and construction cycle index data can be converted into three-dimensional vectors, and the three-dimensional vectors can be input into the pre-trained pipe pile prediction network to obtain the probability distribution corresponding to different pipe pile types. Finally, the target pipe pile type of the target sea area can be determined according to the probability distribution of pipe pile type. For example, the pipe pile type with the highest probability can be taken as the target pipe pile type.

[0079] In an exemplary embodiment, the method for determining the pipe piles in the above-described offshore photovoltaic scenario may further include:

[0080] Data is collected using IoT sensors configured in the current offshore photovoltaic business scenario;

[0081] Environmental, economic, or construction characteristic data are corrected in real time based on sensor data.

[0082] This exemplary embodiment allows for the deployment of Internet of Things (IoT) sensors, such as seabed pressure sensors, depth sensors, and wave radar, in offshore photovoltaic (PV) applications. These sensors collect real-time data on sea depth and wave height. If the collected sensor data deviates from a preset value (e.g., the initial value) by more than a threshold (e.g., a depth change of ±10%), a data update is triggered to correct environmental, economic, or construction characteristic data. Furthermore, sensor data can be re-collected, and geological profile images, marine parameter heat maps, and other data can be regenerated based on the re-collected or corrected data. Additionally, the recommended pipe pile type can be updated.

[0083] An exemplary embodiment of this disclosure also provides a pipe pile determination device in an offshore photovoltaic scenario. (Refer to...) Figure 4 The pipe pile determination device 400 in this offshore photovoltaic scenario may include: a multi-source data acquisition module 410, used to acquire multi-source data of the target sea area in the current offshore photovoltaic business scenario; the multi-source data includes at least environmental feature data, economic feature data, and construction feature data; a key data extraction module 420, used to extract a first type of key data and a second type of key data from the environmental feature data, economic feature data, and construction feature data; an intermediate data acquisition module 430, used to process the first type of key data through a first network layer to obtain first intermediate data, and process the second type of key data through a second network layer to obtain second intermediate data; an intermediate data processing module 440, used to process the first intermediate data and the second intermediate data through a third network layer to obtain target intermediate data; and a pipe pile type determination module 450, used to determine the target pipe pile type of the target sea area in the current offshore photovoltaic business scenario based on the target intermediate data.

[0084] In an exemplary embodiment, the key data extraction module 420 includes: a first image determination unit, configured to extract soil layer distribution data of the target sea area from environmental feature data, and determine a geological profile image of the target sea area based on the soil layer distribution data; a second image determination unit, configured to extract marine parameter index data of the target sea area from environmental feature data, and determine a marine parameter heat map based on the marine parameter index data; the marine parameter index data includes at least sea depth data and wave height data; a first data determination unit, configured to use the geological profile image and marine parameter heat map of the target sea area as a first type of key data; and a second data determination unit, configured to determine a second type of key data based on economic feature data and construction feature data.

[0085] In an exemplary embodiment, the second data determination unit includes: a first correlation data calculation subunit, configured to extract transportation cost data from economic feature data and calculate first correlation data between different time series of transportation cost data; a second correlation data calculation subunit, configured to extract piling resistance data from construction feature data and calculate second correlation data between different time series of piling resistance data; and a second type of key data determination subunit, configured to determine a second type of key data based on the first correlation data and the second correlation data.

[0086] In one exemplary embodiment, a second type of key data determination subunit is used to perform correlation calculations between the first correlation data and the second correlation data, and to use the calculation result as the second type of key data.

[0087] In an exemplary embodiment, the pipe pile determination device in the offshore photovoltaic scenario further includes: a simulation image generation unit, used to generate a simulation image under a preset geological environment based on a geological profile image; and a first data determination unit, used to take the geological profile image of the target sea area, the simulation image under the preset geological environment, and the sea area parameter heat map as a first type of key data.

[0088] In an exemplary embodiment, the intermediate data processing module 440 includes: an evaluation index data acquisition unit, configured to process the first intermediate data and the second intermediate data through a third network layer to obtain evaluation index data for the target sea area; the evaluation index data includes one or more of bearing capacity index data, cost index data, and construction cycle index data; and a pipe pile type determination module 450, including: a target pipe pile type determination unit, configured to process the evaluation index data through a pre-trained pipe pile prediction network and output a pipe pile type probability distribution; and determine the target pipe pile type for the target sea area based on the pipe pile type probability distribution.

[0089] In an exemplary embodiment, the pipe pile determination device in the offshore photovoltaic scenario further includes: a sensor data acquisition module, used to acquire sensor data through IoT sensors configured in the current offshore photovoltaic business scenario; and to correct environmental characteristic data, economic characteristic data, or construction characteristic data in real time based on the sensor data.

[0090] The specific details of each module / unit in the above-mentioned device have been described in detail in the embodiments of the method section. For any undisclosed details, please refer to the embodiments of the method section, and therefore will not be repeated here.

[0091] An exemplary embodiment of this disclosure also provides an electronic device capable of implementing the above-described method.

[0092] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. 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 a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0093] The following reference Figure 5 To describe an electronic device 500 according to such an exemplary embodiment of the present disclosure. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0094] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0095] The storage unit stores program code, which can be executed by the processing unit 510, causing the processing unit 510 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 510 can execute... Figure 1-2 The steps shown are as follows.

[0096] Storage unit 520 may include readable media in the form of volatile storage units, such as random access memory (RAM) 521 and / or cache memory 522, and may further include read-only memory (ROM) 523.

[0097] Storage unit 520 may also include a program / utility 524 having a set (at least one) program module 525, such program module 525 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.

[0098] Bus 530 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 various bus structures.

[0099] Electronic device 500 can also communicate with one or more external devices 600 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 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 550. Furthermore, electronic device 500 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 560. As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. 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 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0100] 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 method according to the exemplary embodiments of this disclosure.

[0101] Exemplary embodiments of this disclosure also provide a computer-readable storage medium having a program product stored thereon capable of implementing the methods described above in this specification. 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 described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0102] Exemplary embodiments of this disclosure also provide a program product for implementing the above-described method, which 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 this disclosure is not limited thereto. In this document, a 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.

[0103] 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 (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, 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.

[0104] 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.

[0105] 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.

[0106] 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 devices 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 can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0107] 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.

[0108] 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 exemplary 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.

[0109] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed 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 disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0110] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is defined only by the appended claims.

Claims

1. A method for pipe pile determination in an offshore photovoltaic scenario, characterized by, include: Acquire multi-source data for the target sea area in the current offshore photovoltaic business scenario; the multi-source data includes at least environmental characteristic data, economic characteristic data, and construction characteristic data; Extract a first type of key data and a second type of key data from the environmental feature data, economic feature data, and construction feature data; the first type of key data is image data, and the second type of key data is time series data; The first type of key data is processed by a first network layer to obtain first intermediate data, and the second type of key data is processed by a second network layer to obtain second intermediate data; the first network layer is a CNN, and the second network layer is an LSTM. The first intermediate data and the second intermediate data are fused together by a third network layer to obtain the target intermediate data; the third network layer is a Transformer. The target pipe pile type in the target sea area of ​​the current offshore photovoltaic business scenario is determined based on the target intermediate data. The extraction of the first type of key data and the second type of key data from the environmental characteristic data, economic characteristic data, and construction characteristic data includes: Soil layer distribution data of the target sea area is extracted from the environmental feature data, and a geological profile image of the target sea area is determined based on the soil layer distribution data. Marine parameter index data of the target sea area is extracted from the environmental feature data, and a sea area parameter heat map is determined based on the sea area parameter index data; the sea area parameter index data includes at least sea area depth data and wave height data; The geological profile image of the target sea area and the heat map of the sea area parameters are used as the first type of key data; Based on the economic characteristic data and construction characteristic data, the second type of key data is determined; The determination of the second type of key data based on the economic characteristic data and construction characteristic data includes: Transportation cost data is extracted from economic characteristic data, and the first correlation data of transportation cost data between different time series is calculated. Extract pile driving resistance data from the construction feature data, and calculate the second correlation data of the pile driving resistance data between different time series; Based on the first correlation data and the second correlation data, the second type of key data is determined; The step of determining the second type of key data based on the first correlation data and the second correlation data includes: The first correlation data and the second correlation data are correlated and calculated, and the calculation result is used as the second type of key data. The step of fusing the first intermediate data and the second intermediate data through a third network layer to obtain the target intermediate data includes: The first intermediate data and the second intermediate data are fused by the third network layer to obtain the evaluation index data of the target sea area; the evaluation index data includes one or more of the following: carrying capacity index data, cost index data, and construction period index data. The step of determining the target pipe pile type in the target sea area of ​​the current offshore photovoltaic business scenario based on the target intermediate data includes: The evaluation index data is processed by a pre-trained pipe pile prediction network to output the probability distribution of pipe pile type. The target pipe pile type for the target sea area is determined based on the probability distribution of the pipe pile type.

2. The method according to claim 1, characterized in that, The method further includes: Based on the geological profile image, a simulation image under a preset geological environment is generated; The use of geological profile images of the target sea area and thermal maps of sea area parameters as the first type of key data includes: The geological profile image of the target sea area, the simulation image of the preset geological environment, and the sea area parameter heat map are used as the first type of key data.

3. The method according to claim 1, characterized in that, The method further includes: Sensor data is collected through IoT sensors configured in the current offshore photovoltaic business scenario; The environmental characteristic data, the economic characteristic data, or the construction characteristic data are corrected in real time based on the sensor data.

4. A pipe pile determination device for offshore photovoltaic applications, characterized in that, include: The multi-source data acquisition module is used to acquire multi-source data of the target sea area in the current offshore photovoltaic business scenario; the multi-source data includes at least environmental characteristic data, economic characteristic data, and construction characteristic data. The key data extraction module is used to extract a first type of key data and a second type of key data from the environmental feature data, economic feature data, and construction feature data; the first type of key data is image data, and the second type of key data is time series data. The intermediate data acquisition module is used to process the first type of key data through a first network layer to obtain first intermediate data, and to process the second type of key data through a second network layer to obtain second intermediate data; the first network layer is a CNN, and the second network layer is an LSTM. An intermediate data processing module is used to fuse the first intermediate data and the second intermediate data through a third network layer to obtain the target intermediate data; the third network layer is a Transformer. The pipe pile type determination module is used to determine the target pipe pile type in the target sea area of ​​the current offshore photovoltaic business scenario based on the target intermediate data. The key data extraction module is configured as follows: Soil layer distribution data of the target sea area is extracted from the environmental feature data, and a geological profile image of the target sea area is determined based on the soil layer distribution data. Marine parameter index data of the target sea area is extracted from the environmental feature data, and a sea area parameter heat map is determined based on the sea area parameter index data; the sea area parameter index data includes at least sea area depth data and wave height data; The geological profile image of the target sea area and the heat map of the sea area parameters are used as the first type of key data; Based on the economic characteristic data and construction characteristic data, the second type of key data is determined; The second type of key data, determined based on the economic characteristic data and construction characteristic data, is configured as follows: Transportation cost data is extracted from economic characteristic data, and the first correlation data of transportation cost data between different time series is calculated. Extract pile driving resistance data from the construction feature data, and calculate the second correlation data of the pile driving resistance data between different time series; Based on the first correlation data and the second correlation data, the second type of key data is determined; The step of determining the second type of key data based on the first correlation data and the second correlation data is configured as follows: The first correlation data and the second correlation data are correlated and calculated, and the calculation result is used as the second type of key data. The intermediate data processing module is configured as follows: The first intermediate data and the second intermediate data are fused by the third network layer to obtain the evaluation index data of the target sea area; the evaluation index data includes one or more of the following: carrying capacity index data, cost index data, and construction period index data. The pipe pile type determination module is configured as follows: The evaluation index data is processed by a pre-trained pipe pile prediction network to output the probability distribution of pipe pile type. The target pipe pile type for the target sea area is determined based on the probability distribution of the pipe pile type.

5. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1-3 by executing the executable instructions.

6. A computer-readable storage medium comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-3.

Images