Fatigue damage prediction method, device and equipment for offshore photovoltaic key component

Abstract

The invention relates to a fatigue damage prediction method, device and equipment for an offshore photovoltaic key component, and relates to the technical field of fatigue damage analysis, and the method comprises the steps: determining first stress distribution of the offshore photovoltaic key component under a service condition according to a first geometric analysis model; determining a second geometric analysis model of the offshore photovoltaic key component according to the dangerous stress area; determining a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model, and determining a feature simulation piece of the offshore photovoltaic key component according to the first stress distribution gradient and the second stress distribution gradient; and determining a fatigue analysis function of the characteristic simulation piece, and determining a maximum stress value and a maximum fatigue life of the characteristic simulation piece according to the fatigue analysis function, so as to perform fatigue damage prediction according to the maximum stress value and the maximum fatigue life. The problem that fatigue damage of key components cannot be analyzed is solved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the technical field of fatigue damage analysis, and in particular, to a fatigue damage prediction method for key components of offshore photovoltaics, a fatigue damage prediction device for key components of offshore photovoltaics, and electronic equipment. Background Art

[0002] Fatigue damage refers to the gradual accumulation of damage to structural materials under cyclic stress loading. Its primary mechanisms are stress concentration caused by cyclic loading, material defects, friction, corrosion, and other factors. Therefore, fatigue analysis can help engineers predict and assess the lifespan of structural components and take appropriate measures to improve their reliability and durability.

[0003] Currently, there is a lack of fatigue damage analysis of key components such as offshore photovoltaic pile foundation column structures and photovoltaic support structures.

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

[0005] The purpose of the present disclosure is to provide a fatigue damage prediction method for key components of offshore photovoltaics, a fatigue damage prediction device for key components of offshore photovoltaics, and an electronic device, thereby at least to a certain extent overcoming the problem of being unable to analyze fatigue damage of key components due to the limitations and defects of related technologies.

[0006] According to one aspect of the present disclosure, a method for predicting fatigue damage of key components of offshore photovoltaic systems is provided, comprising:

[0007] Constructing a first geometric analysis model of a key component of offshore photovoltaics, and determining a first stress distribution of the key component of offshore photovoltaics under a service condition based on the first geometric analysis model;

[0008] determining a dangerous stress area of ​​the key component of the offshore photovoltaic system according to the first stress distribution, and determining a second geometric analysis model of the key component of the offshore photovoltaic system according to the dangerous stress area;

[0009] Determining a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model, and determining a characteristic simulation part of a key component of the offshore photovoltaic system based on the first stress distribution gradient and the second stress distribution gradient;

[0010] A fatigue analysis function of the characteristic simulation component is determined, and a maximum stress value and a maximum fatigue life of the characteristic simulation component are determined according to the fatigue analysis function, so as to perform fatigue damage prediction according to the maximum stress value and the maximum fatigue life.

[0011] In an exemplary embodiment of the present disclosure, a first geometric analysis model of a key component of an offshore photovoltaic system is constructed, and a first stress distribution of the key component of the offshore photovoltaic system under a service condition is determined based on the first geometric analysis model, including:

[0012] Obtaining original geometric models of key components of offshore photovoltaics; wherein the key components include pile column foundation structure components and photovoltaic support structure components;

[0013] Configuring first component performance parameters for the original geometric model; wherein the first component performance parameters include at least one of a first elastic modulus, a first Poisson's ratio, a first tensile strength, a first compressive strength, and a first horizontal bearing capacity of a first component material used to prepare the pile column foundation structure component, and at least one of a second elastic modulus, a second Poisson's ratio, a second tensile strength, a second compressive strength, and a second horizontal bearing capacity of a second component material used to prepare the photovoltaic support structure component;

[0014] Applying a first simulated service load under a simulated service condition to the original geometric model; wherein the simulated service condition is obtained by simulating the actual service condition of the pile column foundation structure component and the photovoltaic support structure component, and the first simulated service load includes at least one of a first weather scenario load, a first pressure load, and a first support force load borne by the pile column foundation structure component during service, and at least one of a second weather scenario load, a second pressure load, and a second support force load borne by the photovoltaic support structure component during service;

[0015] Inputting the original geometric model, the first component performance parameter, and the first simulated service load into a preset content generation model to obtain a first geometric analysis model;

[0016] The first geometric analysis model is input into a preset stress distribution prediction model to obtain a first stress distribution of the key components of the offshore photovoltaic system under service conditions.

[0017] In an exemplary embodiment of the present disclosure, the preset content generation model includes a first embedding mapping layer, a first encoding layer, and a first hybrid expert model layer;

[0018] The original geometric model, the first component performance parameter, and the first simulated service load are input into a preset content generation model to obtain a first geometric analysis model, including:

[0019] generating first basic information to be predicted based on the original geometric model, the first component performance parameter, and the first simulated service load, and generating first context information to be predicted based on a preset first model prompt parameter;

[0020] performing embedding mapping processing on the first basic information to be predicted based on the first embedding mapping layer to obtain a first model feature, and performing embedding mapping processing on the first context information to be predicted based on the first embedding mapping layer to obtain a first context flag sequence;

[0021] Based on the first coding layer, the first model features and the first context marker sequence are encoded to obtain a first context overall representation, and based on the first hybrid expert model layer, the first context marker sequence and the first context overall representation are modeled to obtain a first geometric analysis model.

[0022] In an exemplary embodiment of the present disclosure, the first hybrid expert model layer includes a first gated network model and a plurality of first expert neural network models;

[0023] The first context marker sequence and the first context overall representation are modeled based on the first hybrid expert model layer to obtain a first geometric analysis model, including:

[0024] Determining, based on the first gating network model and the first contextual flag sequence, a first model weight of the first expert neural network model for performing a model generation task in a model fit dimension and a second model weight of the first expert neural network model for performing a model generation task in a model adaptation dimension;

[0025] Determine a first target neural network model required for performing a model generation task on a model fit dimension from the plurality of first expert neural network models according to the first model weight, and determine a second target neural network model required for performing a model generation task on a model fit dimension from the plurality of first expert neural network models according to the second model weight;

[0026] The first context marker sequence and the first context overall representation are respectively input into the first target neural network model and the second target neural network model to obtain the first model prediction result in the model fit dimension and the second model prediction result in the model adaptation dimension, and the first geometric analysis model is determined based on the first model prediction result and the second model prediction result.

[0027] In an exemplary embodiment of the present disclosure, determining a dangerous stress area of ​​a key component of an offshore photovoltaic system according to a first stress distribution, and determining a second geometric analysis model of the key component of the offshore photovoltaic system according to the dangerous stress area includes:

[0028] Determining, based on the first stress distribution, a maximum stress position of the key component of the offshore photovoltaic system and a maximum stress distribution corresponding to the maximum stress position, and determining, based on the maximum stress position, a dangerous stress area of ​​the key component of the offshore photovoltaic system;

[0029] Target geometric model parameters of the dangerous stress area are obtained, and a second geometric analysis model of a key component of offshore photovoltaics is determined based on the original geometric model parameters of the first geometric analysis model and the target geometric model parameters of the dangerous stress area.

[0030] In an exemplary embodiment of the present disclosure, determining a characteristic simulation part of a key component of the offshore photovoltaic system according to the first stress distribution gradient and the second stress distribution gradient includes:

[0031] determining whether a first gradient direction of the first stress distribution gradient and a second gradient direction of the second stress distribution gradient are consistent;

[0032] When it is determined that the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are consistent, using the second geometric analysis model as a characteristic simulation part of the key component of the offshore photovoltaic;

[0033] When it is determined that the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are inconsistent, the second geometric analysis model is adjusted, and the second geometric analysis model after position adjustment is used as a characteristic simulation part of the key component of the offshore photovoltaic.

[0034] In an exemplary embodiment of the present disclosure, determining the fatigue analysis function of the characteristic simulation component includes:

[0035]

[0036] Where N is the fatigue life of the characteristic simulation part, △σ is the stress range of the characteristic simulation part; m is the log 10 N-log 10 In S plot, the inverse slope of the SN curve, log 10 a is the logarithm of the SN curve 10 The intercept of N on the N axis, t ref is the reference thickness of the characteristic simulation part, t is the actual thickness of the characteristic simulation part, and k is the thickness index of the characteristic simulation part.

[0037] According to one aspect of the present disclosure, a fatigue damage prediction device for key components of offshore photovoltaic systems is provided, comprising:

[0038] a first stress distribution determination module, configured to construct a first geometric analysis model of a key component of offshore photovoltaics, and determine a first stress distribution of the key component of offshore photovoltaics under a service condition based on the first geometric analysis model;

[0039] a second geometric analysis model determination module, configured to determine a dangerous stress area of ​​the key component of the offshore photovoltaic system according to the first stress distribution, and determine a second geometric analysis model of the key component of the offshore photovoltaic system according to the dangerous stress area;

[0040] a characteristic simulation component determination module, configured to determine a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model, and determine a characteristic simulation component of a key component of the offshore photovoltaic system based on the first stress distribution gradient and the second stress distribution gradient;

[0041] The fatigue damage prediction module is used to determine the fatigue analysis function of the characteristic simulation component, and determine the maximum stress value and maximum fatigue life of the characteristic simulation component according to the fatigue analysis function, so as to predict fatigue damage according to the maximum stress value and maximum fatigue life.

[0042] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for predicting fatigue damage of key components of offshore photovoltaics described in any one of the above is implemented.

[0043] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0044] processor; and

[0045] a memory for storing executable instructions of the processor;

[0046] The processor is configured to execute any one of the above-mentioned fatigue damage prediction methods for key components of offshore photovoltaics by executing the executable instructions.

[0047] The embodiment of the present disclosure provides a fatigue damage prediction method for key components of offshore photovoltaics. On the one hand, a first geometric analysis model of the key components of offshore photovoltaics is constructed, and based on the first geometric analysis model, a first stress distribution of the key components of offshore photovoltaics under service conditions is determined; then, a dangerous stress area of ​​the key components of offshore photovoltaics is determined based on the first stress distribution, and a second geometric analysis model of the key components of offshore photovoltaics is determined based on the dangerous stress area; then, a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model are determined, and a characteristic simulation part of the key components of offshore photovoltaics is determined based on the first stress distribution gradient and the second stress distribution gradient; finally, a fatigue analysis function of the characteristic simulation part is determined, and a maximum stress value and a maximum fatigue life of the characteristic simulation part are determined based on the fatigue analysis function, so as to predict fatigue damage based on the maximum stress value and the maximum fatigue life, thereby realizing fatigue damage prediction of key components of offshore photovoltaics and solving the problem that fatigue damage of key components of offshore photovoltaics cannot be predicted in the prior art; on the other hand, since the maximum stress value and the maximum fatigue life of the characteristic simulation part can be determined based on the fatigue analysis function of the characteristic simulation part of the key components of offshore photovoltaics, the accuracy of the obtained fatigue damage prediction results is improved.

[0048] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0050] Figure 1 A flowchart schematically illustrates a method for predicting fatigue damage of a key component of offshore photovoltaics according to an exemplary embodiment of the present disclosure.

[0051] Figure 2 The following schematically shows an example structure diagram of key components of offshore photovoltaics according to an example embodiment of the present disclosure.

[0052] Figure 3 A schematic diagram shows an example structure of a preset content generation model according to an exemplary embodiment of the present disclosure.

[0053] Figure 4 A diagram schematically illustrates an example structure of a first hybrid expert model layer according to an exemplary embodiment of the present disclosure.

[0054] Figure 5 A structural example diagram of a preset stress distribution prediction model according to an example embodiment of the present disclosure is schematically shown.

[0055] Figure 6 An example diagram schematically illustrates calculation results of fatigue damage of a key component according to an example embodiment of the present disclosure.

[0056] Figure 7 A structural example diagram of a fatigue damage prediction device for a key component of offshore photovoltaics according to an example embodiment of the present disclosure is schematically shown.

[0057] Figure 8 An electronic device for implementing a fatigue damage prediction method for key components of offshore photovoltaics according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0058] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and will fully convey the concepts of the example 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. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0059] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0060] This exemplary embodiment first provides a fatigue damage prediction method for key components of offshore photovoltaics, which can be run on terminal devices, servers, server clusters, or cloud servers; of course, those skilled in the art can also run the disclosed method on other platforms as needed, and this exemplary embodiment does not specifically limit this. Figure 1As shown, the fatigue damage prediction method of the key components of offshore photovoltaics may include the following steps:

[0061] Step S110: constructing a first geometric analysis model of a key component of offshore photovoltaics, and determining a first stress distribution of the key component of offshore photovoltaics under a service condition based on the first geometric analysis model;

[0062] Step S120. Determine a dangerous stress area of ​​a key component of offshore photovoltaics based on the first stress distribution, and determine a second geometric analysis model of the key component of offshore photovoltaics based on the dangerous stress area;

[0063] Step S130: determining a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model, and determining a characteristic simulation part of a key component of the offshore photovoltaic system based on the first stress distribution gradient and the second stress distribution gradient;

[0064] Step S140: Determine the fatigue analysis function of the characteristic simulation component, and determine the maximum stress value and the maximum fatigue life of the characteristic simulation component according to the fatigue analysis function, so as to perform fatigue damage prediction according to the maximum stress value and the maximum fatigue life.

[0065] In the fatigue damage prediction method of key components of offshore photovoltaics described above, on the one hand, a first geometric analysis model of the key components of offshore photovoltaics is constructed, and based on the first geometric analysis model, the first stress distribution of the key components of offshore photovoltaics under service conditions is determined; then, the dangerous stress area of ​​the key components of offshore photovoltaics is determined based on the first stress distribution, and the second geometric analysis model of the key components of offshore photovoltaics is determined based on the dangerous stress area; then, the first stress distribution gradient of the dangerous stress area and the second stress distribution gradient of the second geometric analysis model are determined, and based on the first stress distribution gradient and the second stress distribution gradient, the characteristic simulation part of the key components of offshore photovoltaics is determined; finally, the fatigue analysis function of the characteristic simulation part is determined, and the maximum stress value and the maximum fatigue life of the characteristic simulation part are determined based on the fatigue analysis function, so as to predict fatigue damage based on the maximum stress value and the maximum fatigue life, thereby realizing the prediction of fatigue damage of key components of offshore photovoltaics, and solving the problem that fatigue damage of key components of offshore photovoltaics cannot be predicted in the prior art; on the other hand, since the maximum stress value and the maximum fatigue life of the characteristic simulation part can be determined based on the fatigue analysis function of the characteristic simulation part of the key components of offshore photovoltaics, the accuracy of the obtained fatigue damage prediction results is improved.

[0066] Hereinafter, the fatigue damage prediction method of key components of offshore photovoltaic systems described in the exemplary embodiments of the present disclosure will be further explained and illustrated with reference to the accompanying drawings.

[0067] First, the key components of offshore photovoltaics involved in the exemplary embodiments of the present disclosure are explained and illustrated. Figure 2 As shown, the key components of offshore photovoltaics recorded in the example embodiments of the present disclosure may include pile column foundation structure components 210 and photovoltaic support structure components; wherein the pile column foundation structure components and the photovoltaic support structure components may be connected by welding, and of course may also be linked by other means; further, the photovoltaic support structure components recorded herein may include but are not limited to diagonal braces 201, steel column structures 202 and diagonal beams 203, etc.; the photovoltaic support is connected to the pile foundation column 210 in the offshore photovoltaic scene through the steel column structure, the diagonal brace can be connected to the steel column structure, and the diagonal beam can be connected to the diagonal brace. The specific connection method may be hinged or riveted, and this example does not impose special restrictions on this; at the same time, the diagonal beam and the diagonal brace are used to support the photovoltaic panel (also known as photovoltaic module) 220, and the photovoltaic panel and the diagonal beam can be connected through the sandalwood bar 230.

[0068] Next, the preset content generation model involved in the exemplary embodiment of the present disclosure is explained and illustrated. Figure 3 As shown, the preset content generation model described herein may include a first input layer 301, a first embedding mapping layer 302, a first encoding layer 303, a first hybrid expert model layer 304, and a first output layer 305; wherein the first hybrid expert model layer described herein may include a first gating network model and multiple first expert neural network models. For a specific structural example diagram, please refer to Figure 4 At the same time, the role of each model layer in the model generation task will be described in detail later, and will not be further elaborated here.

[0069] The preset stress distribution prediction model described in the exemplary embodiment of the present disclosure will be explained and illustrated. Figure 5 As shown, the preset stress distribution prediction model described herein may include a second input layer 501, a second embedding mapping layer 502, a second encoding layer 503, a second hybrid expert model layer 504, and a second output layer 505. The specific structure of the second hybrid expert model layer described herein is similar to that of the first hybrid expert model layer and will not be further described here. The role of each model layer in the stress distribution prediction process will be described in detail later and will not be further described here.

[0070] The following will be combined Figure 2-Figure 5 right Figure 1 The fatigue damage prediction method of key components of offshore photovoltaics shown in the article is further explained and illustrated. Specifically:

[0071] In step S110 , a first geometric analysis model of a key component of offshore photovoltaics is constructed, and based on the first geometric analysis model, a first stress distribution of the key component of offshore photovoltaics under a service condition is determined.

[0072] In this example embodiment, first, a first geometric analysis model of a key component of offshore photovoltaics is constructed; specifically, this can be achieved in the following manner: an original geometric model of a key component of offshore photovoltaics is obtained; first component performance parameters are configured for the original geometric model; wherein the first component performance parameters recorded here may include but are not limited to a first elastic modulus, a first Poisson's ratio, a first tensile strength, a first compressive strength, and a first horizontal bearing capacity, etc., of a first component material used to prepare a pile column foundation structure component, and a second elastic modulus, a second Poisson's ratio, a second tensile strength, a second compressive strength, and a second horizontal bearing capacity, etc., of a second component material used to prepare a photovoltaic support structure component; and The first simulated service load under the simulated service condition is applied to the model; wherein, the simulated service condition recorded here is obtained by simulating the actual service condition of the pile column foundation structure components and the photovoltaic support structure components, and the first simulated service load may include but is not limited to the first weather scene load, the first pressure load and the first support force load borne by the pile column foundation structure components during the service process, and the second weather scene load, the second pressure load and the second support force load borne by the photovoltaic support structure components during the service process; the original geometric model, the first component performance parameters and the first simulated service load are input into the preset content generation large model to obtain the first geometric analysis model. Furthermore, the original geometric model recorded here refers to the overall collective model composed of the pile column foundation structure components and the photovoltaic support structure components; in the actual application process, if it is necessary to construct the first geometric analysis model, it is first necessary to determine the above-mentioned component performance parameters and simulated service loads, and then generate the first geometric analysis model based on the corresponding content generation large model.

[0073] In an exemplary embodiment, inputting the original geometric model, first component performance parameters, and first simulated service load into a preset content generation macromodel to obtain a first geometric analysis model can be achieved by: generating first basic information to be predicted based on the original geometric model, first component performance parameters, and first simulated service load, and generating first context information to be predicted based on preset first model prompt parameters; performing embedding mapping processing on the first basic information to be predicted based on the first embedding mapping layer to obtain first model features, and performing embedding mapping processing on the first context information to be predicted based on the first embedding mapping layer to obtain a first context marker sequence; encoding the first model features and the first context marker sequence based on the first encoding layer to obtain a first context overall representation, and performing model generation on the first context marker sequence and the first context overall representation based on the first hybrid expert model layer to obtain the first geometric analysis model. The preset first model parameter prompt information recorded herein can, for example, be: Your task is xxx, you need to generate xxxx based on the input data; the generated result needs to be displayed in the form of xxx; the generated result may include x, etc. In the process of actual application, the corresponding first model parameter prompt information can be set according to actual needs, and this example does not impose special restrictions on this. Furthermore, the embedding mapping layer recorded here can include an Embedding embedding mapping layer and a Bert embedding mapping layer. In the process of actual application, the first basic information to be predicted can be embedded and mapped based on the Embedding embedding mapping layer to obtain the first model feature, and the first context information to be predicted can be embedded and mapped based on the Bert embedding mapping layer to obtain the first context flag sequence; the encoding layer recorded here can be a bidirectional multi-layer Transformer.

[0074] In an example embodiment, model generation is performed on the first context marker sequence and the first context overall representation based on the first hybrid expert model layer to obtain a first geometric analysis model, which can be achieved as follows: based on the first gating network model and according to the first context marker sequence, a first model weight of the first expert neural network model in performing a model generation task in the model fit dimension and a second model weight of the first expert neural network model in performing a model generation task in the model fitness dimension are determined; according to the first model weight, a first target neural network model required for performing the model generation task in the model fit dimension is determined from the multiple first expert neural network models, and according to the second model weight, a second target neural network model required for performing the model generation task in the model fitness dimension is determined from the multiple first expert neural network models; the first context marker sequence and the first context overall representation are input into the first target neural network model and the second target neural network model respectively to obtain a first model prediction result in the model fit dimension and a second model prediction result in the model fitness dimension, and a first geometric analysis model is determined based on the first model prediction result and the second model prediction result. Specifically, the model fit dimension recorded here refers to the fit between the obtained first geometric analysis model and the original combined model; at the same time, the model fit dimension recorded here refers to the fit between the generated first geometric analysis model and the original geometric model; the model adaptation dimension recorded here refers to the adaptability between the generated first geometric analysis model and the first component performance parameters and the first simulated service load; further, after obtaining the first model prediction results and the second model prediction results, the first model prediction results and the second model prediction results can be weightedly summed to obtain the first geometric analysis model; the weight values ​​used in the weighted summation process can be determined by themselves according to actual needs, or can be determined according to the corresponding weight value prediction model. This example does not impose any special restrictions on this.

[0075] Secondly, based on the first geometric analysis model, the first stress distribution of the key components of the offshore photovoltaic system under the service condition is determined; specifically, this can be achieved by the following method: inputting the first geometric analysis model into a preset stress distribution prediction model to obtain the first stress distribution of the key components of the offshore photovoltaic system under the service condition. Specifically, the specific determination process of the first stress distribution can be achieved by the following method: generating second basic information to be predicted based on the first geometric analysis model, the first component performance parameters and the first simulated service load, and generating first context information to be predicted based on the preset second model prompt parameters; embedding and mapping the second basic information to be predicted based on the second embedding mapping layer to obtain second model features, and embedding and mapping the second context information to be predicted based on the second embedding mapping layer to obtain a second context marker sequence; encoding the second model features and the second context marker sequence based on the second encoding layer to obtain a second context overall representation, and performing stress distribution prediction on the second context marker sequence and the second context overall representation based on the second hybrid expert model layer to obtain the first stress distribution of the key components of the offshore photovoltaic system under the service condition. The preset second model parameter prompt information recorded here may, for example, be: Your task is xxx. You need to determine an example stress distribution diagram for the first geometric analysis model based on the input data; the generated results need to be displayed in the form of xxx; the generated results may include x, ...; in the process of generating the stress distribution, it is necessary to determine it from two dimensions. In actual application, the corresponding first model parameter prompt information can be set according to actual needs, and this example does not impose any special restrictions on this.

[0076] In an example embodiment, stress distribution prediction is performed on the second context marker sequence and the second context overall representation based on the second hybrid expert model layer to obtain the first stress distribution of the key components of offshore photovoltaics under service conditions. This can be achieved as follows: based on the second gated network model and the second context marker sequence, the third model weight of the second expert neural network model in performing the stress distribution prediction task in the constant load dimension and the fourth model weight of the stress distribution prediction task in the weather load dimension are determined; according to the third model weight and the fourth model weight, the third target neural network model required for performing the stress distribution prediction task in the constant load dimension and the fourth target neural network model required for performing the stress distribution prediction task in the weather load dimension are determined from the second expert neural network model; the second context marker sequence and the second context overall representation are input into the third target neural network model and the fourth target neural network model respectively to obtain the constant load stress distribution results in the constant load dimension and the weather load stress distribution results in the weather load dimension, and the first stress distribution of the key components of offshore photovoltaics under service conditions is determined based on the constant load stress distribution results and the weather load stress distribution results. Among them, the constant load recorded here refers to the constant load that the key components need to bear, such as the key components' own weight and the weight of other components they need to bear; the weather load recorded here refers to the load that the key components need to bear in various weather conditions such as rain, snow, wind, and earthquakes.

[0077] In step S120 , a dangerous stress area of ​​the key component of the offshore photovoltaic system is determined according to the first stress distribution, and a second geometric analysis model of the key component of the offshore photovoltaic system is determined according to the dangerous stress area.

[0078] Specifically, the specific determination process of the dangerous stress area and the specific determination process of the second geometric analysis model can be achieved in the following manner: according to the first stress distribution, the maximum stress position of the key component of the offshore photovoltaic system and the maximum stress distribution corresponding to the maximum stress position are determined, and the dangerous stress area of ​​the key component of the offshore photovoltaic system is determined according to the maximum stress position; the target geometric model parameters of the dangerous stress area are obtained, and the second geometric analysis model of the key component of the offshore photovoltaic system is determined according to the original geometric model parameters of the first geometric analysis model and the target geometric model parameters of the dangerous stress area. The dangerous stress area recorded here refers to the position corresponding to the maximum stress node in the first stress distribution of the first geometric analysis model; further, after obtaining the stress distribution of the maximum stress position, the maximum stress position can be selected as the dangerous stress area of ​​the key component; then, the target geometric model parameters of the dangerous stress area of ​​the key component are obtained, and based on the principle of geometric similarity, the second geometric analysis model of the key component of the offshore photovoltaic system is determined according to the original geometric model parameters of the first geometric analysis model and the target geometric model parameters.

[0079] In step S130, a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model are determined, and characteristic simulation parts of key components of the offshore photovoltaic system are determined based on the first stress distribution gradient and the second stress distribution gradient.

[0080] Specifically, the first stress distribution gradient can be determined based on the stress distribution of the dangerous stress area, and the stress distribution of the dangerous stress area can also be determined based on a preset stress distribution prediction model. The specific determination process is similar to the specific determination process of the first stress distribution, and no further details are given here; the second stress distribution gradient can be determined based on the second stress distribution of the second geometric analysis model. The specific determination process of the second stress distribution is similar to the specific determination process of the first stress distribution, and no further details are given here.

[0081] Secondly, a characteristic simulation component of a key component of offshore photovoltaics is determined. Specifically, this can be achieved by: determining whether the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are consistent; when the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are determined to be consistent, using the second geometric analysis model as the characteristic simulation component of the key component of offshore photovoltaics; when the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are determined to be inconsistent, adjusting the second geometric analysis model and using the second geometric analysis model after the position adjustment as the characteristic simulation component of the key component of offshore photovoltaics. That is, in actual application, if it is necessary to complete the design of the characteristic simulation component of the key component of offshore photovoltaics, it is necessary to follow the following design indicators: ensure that the maximum stress node in the stress distribution of the characteristic simulation component is consistent with the dangerous point in the dangerous stress area, and also ensure that the stress distribution gradient in the characteristic simulation component is consistent with the stress gradient of the first geometric analysis model along the stress drop direction; further, the specific optimization process of the second geometric analysis model of the characteristic simulation component is: by continuously adjusting the positions of relevant components in the characteristic simulation component, the first gradient direction is consistent with the second gradient direction.

[0082] In step S140 , a fatigue analysis function of the characteristic simulation component is determined, and a maximum stress value and a maximum fatigue life of the characteristic simulation component are determined based on the fatigue analysis function, so as to perform fatigue damage prediction based on the maximum stress value and the maximum fatigue life.

[0083] In an exemplary embodiment of the present disclosure, first, a fatigue analysis function of a characteristic simulation component is determined; specifically, the fatigue analysis function may be expressed as follows:

[0084]

[0085] Where N is the fatigue life of the characteristic simulation part, △σ is the stress range of the characteristic simulation part, which can be determined according to the second stress distribution of the second geometric analysis model; m is the log 10 N-log 10 In S plot, the inverse slope of the SN curve, log 10 a is the logarithm of the SN curve 10 The intercept of N on the N axis, t ref is the reference thickness of the characteristic simulation part, t is the actual thickness of the characteristic simulation part, and k is the thickness index of the characteristic simulation part. Further, for the tubular joint, t ref The value of can be 32mm; for circumferential welds, t refThe value of can be 25mm; that is, for the pile column foundation structure components, t ref The value can be 25mm.

[0086] Then, the SN curve is constructed according to the fatigue analysis function, and the maximum stress value and maximum fatigue life of the characteristic simulation part are determined based on the obtained SN curve; finally, the fatigue damage of the key component is predicted based on the current actual stress and maximum stress value, the current actual life and the maximum fatigue life; the calculation results of the fatigue damage of the key component can be referred to Figure 6 shown; and, by Figure 6 From the calculation results shown, it can be seen that the maximum fatigue cumulative damage of the pile column foundation structure components and the photovoltaic support structure components is 0.52, that is, the maximum value of the fatigue cumulative damage of the pile column foundation structure components and the photovoltaic support structure components is less than 1, and has not reached the corresponding fatigue threshold, so no maintenance is required; further, if the maximum value of the fatigue cumulative damage of the pile column foundation structure components and the photovoltaic support structure components is infinitely close to 1, it is determined that the fatigue cumulative damage of the pile column foundation structure components and the photovoltaic support structure components has reached the fatigue threshold, and maintenance is required.

[0087] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0088] The exemplary embodiment of the present disclosure also provides a fatigue damage prediction device for key components of offshore photovoltaics. Figure 7 As shown, the fatigue damage prediction device for key components of offshore photovoltaics may include a first stress distribution determination module 710, a second geometric analysis model determination module 720, a feature simulation component determination module 730, and a fatigue damage prediction module 740.

[0089] The first stress distribution determination module 710 may be used to construct a first geometric analysis model of a key component of offshore photovoltaics, and determine a first stress distribution of the key component of offshore photovoltaics under a service condition based on the first geometric analysis model;

[0090] The second geometric analysis model determination module 720 may be configured to determine a dangerous stress region of the key component of the offshore photovoltaic system according to the first stress distribution, and determine a second geometric analysis model of the key component of the offshore photovoltaic system according to the dangerous stress region;

[0091] The characteristic simulation component determination module 730 may be configured to determine a first stress distribution gradient of the dangerous stress region and a second stress distribution gradient of the second geometric analysis model, and determine a characteristic simulation component of a key component of the offshore photovoltaic system based on the first stress distribution gradient and the second stress distribution gradient;

[0092] The fatigue damage prediction module 740 can be used to determine the fatigue analysis function of the characteristic simulation component, and determine the maximum stress value and maximum fatigue life of the characteristic simulation component based on the fatigue analysis function, so as to perform fatigue damage prediction based on the maximum stress value and maximum fatigue life.

[0093] In an exemplary embodiment of the present disclosure, a first geometric analysis model of a key component of offshore photovoltaics is constructed, and based on the first geometric analysis model, a first stress distribution of the key component of offshore photovoltaics under service conditions is determined, including: obtaining an original geometric model of the key component of offshore photovoltaics; wherein the key component includes a pile column foundation structure component and a photovoltaic support structure component; configuring first component performance parameters for the original geometric model; wherein the first component performance parameters include at least one of a first elastic modulus, a first Poisson's ratio, a first tensile strength, a first compressive strength and a first horizontal bearing capacity of a first component material used to prepare the pile column foundation structure component, and at least one of a second elastic modulus, a second Poisson's ratio, a second tensile strength, a second compressive strength and a second horizontal bearing capacity of a second component material used to prepare the photovoltaic support structure component; configuring first component performance parameters for the original geometric model; wherein the first component performance parameters include at least one of a first elastic modulus, a first Poisson's ratio, a first tensile strength, a first compressive strength and a first horizontal bearing capacity of a first component material used to prepare the pile column foundation structure component; The first simulated service load under the simulated service condition is applied to the original geometric model; wherein, the simulated service condition is obtained by simulating the real service condition of the pile column foundation structure component and the photovoltaic support structure component, and the first simulated service load includes at least one of the first weather scenario load, the first pressure load and the first support force load borne by the pile column foundation structure component during service, and at least one of the second weather scenario load, the second pressure load and the second support force load borne by the photovoltaic support structure component during service; the original geometric model, the first component performance parameters and the first simulated service load are input into the preset content generation model to obtain a first geometric analysis model; the first geometric analysis model is input into the preset stress distribution prediction model to obtain the first stress distribution of the key components of the offshore photovoltaic under the service condition.

[0094] In an exemplary embodiment of the present disclosure, the preset content generation large model includes a first embedding mapping layer, a first encoding layer and a first hybrid expert model layer; wherein the original geometric model, the first component performance parameters and the first simulated service load are input into the preset content generation large model to obtain a first geometric analysis model, including: generating the first basic information to be predicted based on the original geometric model, the first component performance parameters and the first simulated service load, and generating the first context information to be predicted based on the preset first model prompt parameters; embedding and mapping the first basic information to be predicted based on the first embedding mapping layer to obtain a first model feature, and embedding and mapping the first context information to be predicted based on the first embedding mapping layer to obtain a first context marker sequence; encoding the first model feature and the first context marker sequence based on the first encoding layer to obtain a first context overall representation, and model generating the first context marker sequence and the first context overall representation based on the first hybrid expert model layer to obtain a first geometric analysis model.

[0095] In an exemplary embodiment of the present disclosure, the first hybrid expert model layer includes a first gating network model and multiple first expert neural network models; wherein, based on the first hybrid expert model layer, the first context marker sequence and the first context overall representation are model-generated to obtain a first geometric analysis model, including: determining the first model weight of the first expert neural network model in performing the model generation task in the model fit dimension and the second model weight of the first expert neural network model in performing the model generation task in the model fitness dimension based on the first context marker sequence; determining the first target neural network model required for performing the model generation task in the model fit dimension from the multiple first expert neural network models according to the first model weight, and determining the second target neural network model required for performing the model generation task in the model fitness dimension from the multiple first expert neural network models according to the second model weight; inputting the first context marker sequence and the first context overall representation into the first target neural network model and the second target neural network model respectively, obtaining the first model prediction result in the model fit dimension and the second model prediction result in the model fitness dimension, and determining the first geometric analysis model based on the first model prediction result and the second model prediction result.

[0096] In an exemplary embodiment of the present disclosure, a dangerous stress area of ​​a key component of offshore photovoltaics is determined according to a first stress distribution, and a second geometric analysis model of the key component of offshore photovoltaics is determined according to the dangerous stress area, including: determining the maximum stress position of the key component of offshore photovoltaics and the maximum stress distribution corresponding to the maximum stress position according to the first stress distribution, and determining the dangerous stress area of ​​the key component of offshore photovoltaics according to the maximum stress position; obtaining target geometric model parameters of the dangerous stress area, and determining the second geometric analysis model of the key component of offshore photovoltaics according to the original geometric model parameters of the first geometric analysis model and the target geometric model parameters of the dangerous stress area.

[0097] In an exemplary embodiment of the present disclosure, a characteristic simulation part of the key component of the offshore photovoltaic is determined based on the first stress distribution gradient and the second stress distribution gradient, including: determining whether the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are consistent; when it is determined that the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are consistent, the second geometric analysis model is used as the characteristic simulation part of the key component of the offshore photovoltaic; when it is determined that the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are inconsistent, the second geometric analysis model is adjusted, and the second geometric analysis model after position adjustment is used as the characteristic simulation part of the key component of the offshore photovoltaic.

[0098] In an exemplary embodiment of the present disclosure, determining the fatigue analysis function of the characteristic simulation component includes:

[0099] Where N is the fatigue life of the characteristic simulation part, △σ is the stress range of the characteristic simulation part; m is the log 10 N-log 10 In S plot, the inverse slope of the SN curve, log 10 a is the logarithm of the SN curve 10 The intercept of N on the N axis, t ref is the reference thickness of the characteristic simulation part, t is the actual thickness of the characteristic simulation part, and k is the thickness index of the characteristic simulation part.

[0100] The specific details of each module in the above-mentioned fatigue damage prediction device for key components of offshore photovoltaics have been described in detail in the corresponding fatigue damage prediction method for key components of offshore photovoltaics, and will not be repeated here.

[0101] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0102] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0103] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. Those skilled in the art will appreciate that various aspects of the present disclosure can be implemented as a system, method, or program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as a circuit, module, or system.

[0104] Refer to the following Figure 8 800 according to this embodiment of the present disclosure will be described. Figure 8 The electronic device 800 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0105] like Figure 8 As shown, electronic device 800 is implemented as a general-purpose computing device. Components of electronic device 800 may include, but are not limited to, the aforementioned at least one processing unit 810, the aforementioned at least one storage unit 820, a bus 830 connecting various system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0106] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps described in the "Exemplary Method" section of the present disclosure according to various exemplary embodiments. For example, the processing unit 810 can perform the following steps: Figure 1Step S110 shown in: constructing a first geometric analysis model of the key components of offshore photovoltaics, and determining the first stress distribution of the key components of offshore photovoltaics under service conditions based on the first geometric analysis model; step S120: determining the dangerous stress area of ​​the key components of offshore photovoltaics based on the first stress distribution, and determining the second geometric analysis model of the key components of offshore photovoltaics based on the dangerous stress area; step S130: determining the first stress distribution gradient of the dangerous stress area and the second stress distribution gradient of the second geometric analysis model, and determining the characteristic simulation parts of the key components of offshore photovoltaics based on the first stress distribution gradient and the second stress distribution gradient; step S140: determining the fatigue analysis function of the characteristic simulation parts, and determining the maximum stress value and maximum fatigue life of the characteristic simulation parts based on the fatigue analysis function, so as to predict fatigue damage based on the maximum stress value and the maximum fatigue life.

[0107] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0108] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0109] Bus 830 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0110] The electronic device 800 can also communicate with one or more external devices 900 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 800, and / or any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 850. Furthermore, the electronic device 800 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0111] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0112] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present disclosure.

[0113] According to an embodiment of the present disclosure, a program product for implementing the above-mentioned method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be 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, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0114] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0115] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of 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 that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0116] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0117] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0118] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0119] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not invented herein. The specification and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

Claims

1. A fatigue damage prediction method for key components of offshore photovoltaics, characterized in that: include: Constructing a first geometric analysis model of a key component of offshore photovoltaics, and determining a first stress distribution of the key component of offshore photovoltaics under a service condition based on the first geometric analysis model; determining a dangerous stress area of ​​the key component of the offshore photovoltaic system according to the first stress distribution, and determining a second geometric analysis model of the key component of the offshore photovoltaic system according to the dangerous stress area; Determining a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model, and determining a characteristic simulation part of a key component of the offshore photovoltaic system based on the first stress distribution gradient and the second stress distribution gradient; A fatigue analysis function of the characteristic simulation component is determined, and a maximum stress value and a maximum fatigue life of the characteristic simulation component are determined according to the fatigue analysis function, so as to perform fatigue damage prediction according to the maximum stress value and the maximum fatigue life.

2. The fatigue damage prediction method for key components of offshore photovoltaics according to claim 1 is characterized in that: Constructing a first geometric analysis model of key components of offshore photovoltaics, and determining the first stress distribution of the key components of offshore photovoltaics under service conditions based on the first geometric analysis model, including: Obtaining original geometric models of key components of offshore photovoltaics; wherein the key components include pile column foundation structure components and photovoltaic support structure components; Configuring first component performance parameters for the original geometric model; wherein the first component performance parameters include at least one of a first elastic modulus, a first Poisson's ratio, a first tensile strength, a first compressive strength, and a first horizontal bearing capacity of a first component material used to prepare the pile column foundation structure component, and at least one of a second elastic modulus, a second Poisson's ratio, a second tensile strength, a second compressive strength, and a second horizontal bearing capacity of a second component material used to prepare the photovoltaic support structure component; Applying a first simulated service load under a simulated service condition to the original geometric model; wherein the simulated service condition is obtained by simulating the actual service condition of the pile column foundation structure component and the photovoltaic support structure component, and the first simulated service load includes at least one of a first weather scenario load, a first pressure load, and a first support force load borne by the pile column foundation structure component during service, and at least one of a second weather scenario load, a second pressure load, and a second support force load borne by the photovoltaic support structure component during service; Inputting the original geometric model, the first component performance parameter, and the first simulated service load into a preset content generation model to obtain a first geometric analysis model; The first geometric analysis model is input into a preset stress distribution prediction model to obtain a first stress distribution of the key components of the offshore photovoltaic system under service conditions.

3. The fatigue damage prediction method for key components of offshore photovoltaics according to claim 2 is characterized in that: The preset content generation model includes a first embedding mapping layer, a first encoding layer and a first hybrid expert model layer; The original geometric model, the first component performance parameter, and the first simulated service load are input into a preset content generation model to obtain a first geometric analysis model, including: generating first basic information to be predicted based on the original geometric model, the first component performance parameter, and the first simulated service load, and generating first context information to be predicted based on a preset first model prompt parameter; performing embedding mapping processing on the first basic information to be predicted based on the first embedding mapping layer to obtain a first model feature, and performing embedding mapping processing on the first context information to be predicted based on the first embedding mapping layer to obtain a first context flag sequence; Based on the first coding layer, the first model features and the first context marker sequence are encoded to obtain a first context overall representation, and based on the first hybrid expert model layer, the first context marker sequence and the first context overall representation are modeled to obtain a first geometric analysis model.

4. The fatigue damage prediction method for key components of offshore photovoltaics according to claim 3 is characterized in that: The first hybrid expert model layer includes a first gating network model and a plurality of first expert neural network models; The first context marker sequence and the first context overall representation are modeled based on the first hybrid expert model layer to obtain a first geometric analysis model, including: Determining, based on the first gating network model and the first contextual flag sequence, a first model weight of the first expert neural network model for performing a model generation task in a model fit dimension and a second model weight of the first expert neural network model for performing a model generation task in a model adaptation dimension; Determine a first target neural network model required for performing a model generation task on a model fit dimension from the plurality of first expert neural network models according to the first model weight, and determine a second target neural network model required for performing a model generation task on a model fit dimension from the plurality of first expert neural network models according to the second model weight; The first context marker sequence and the first context overall representation are respectively input into the first target neural network model and the second target neural network model to obtain the first model prediction result in the model fit dimension and the second model prediction result in the model adaptation dimension, and the first geometric analysis model is determined based on the first model prediction result and the second model prediction result.

5. The fatigue damage prediction method for key components of offshore photovoltaics according to claim 1 is characterized in that: Determining a dangerous stress area of ​​a key component of offshore photovoltaics according to the first stress distribution, and determining a second geometric analysis model of the key component of offshore photovoltaics according to the dangerous stress area, including: Determining, based on the first stress distribution, a maximum stress position of the key component of the offshore photovoltaic system and a maximum stress distribution corresponding to the maximum stress position, and determining, based on the maximum stress position, a dangerous stress area of ​​the key component of the offshore photovoltaic system; Target geometric model parameters of the dangerous stress area are obtained, and a second geometric analysis model of a key component of offshore photovoltaics is determined based on the original geometric model parameters of the first geometric analysis model and the target geometric model parameters of the dangerous stress area.

6. The fatigue damage prediction method for key components of offshore photovoltaics according to claim 1 is characterized in that: Determining a characteristic simulation part of a key component of the offshore photovoltaic system according to the first stress distribution gradient and the second stress distribution gradient includes: determining whether a first gradient direction of the first stress distribution gradient and a second gradient direction of the second stress distribution gradient are consistent; When it is determined that the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are consistent, using the second geometric analysis model as a characteristic simulation part of the key component of the offshore photovoltaic; When it is determined that the first gradient direction of the first stress distribution gradient and the second gradient direction of the second stress distribution gradient are inconsistent, the second geometric analysis model is adjusted, and the second geometric analysis model after position adjustment is used as a characteristic simulation part of the key component of the offshore photovoltaic.

7. The fatigue damage prediction method for key components of offshore photovoltaics according to claim 1, characterized in that: Determining a fatigue analysis function of the characteristic simulation component includes: Where N is the fatigue life of the characteristic simulation part, △σ is the stress range of the characteristic simulation part; m is the log 10 N-log 10 In S plot, the inverse slope of the SN curve, log 10 a is the logarithm of the SN curve 10 The intercept of N on the N axis, t ref is the reference thickness of the characteristic simulation part, t is the actual thickness of the characteristic simulation part, and k is the thickness index of the characteristic simulation part.

8. A fatigue damage prediction device for key components of offshore photovoltaics, characterized in that: include: a first stress distribution determination module, configured to construct a first geometric analysis model of a key component of offshore photovoltaics, and determine a first stress distribution of the key component of offshore photovoltaics under a service condition based on the first geometric analysis model; a second geometric analysis model determination module, configured to determine a dangerous stress area of ​​the key component of the offshore photovoltaic system according to the first stress distribution, and determine a second geometric analysis model of the key component of the offshore photovoltaic system according to the dangerous stress area; a characteristic simulation component determination module, configured to determine a first stress distribution gradient of the dangerous stress area and a second stress distribution gradient of the second geometric analysis model, and determine a characteristic simulation component of a key component of the offshore photovoltaic system based on the first stress distribution gradient and the second stress distribution gradient; The fatigue damage prediction module is used to determine the fatigue analysis function of the characteristic simulation component, and determine the maximum stress value and maximum fatigue life of the characteristic simulation component according to the fatigue analysis function, so as to predict fatigue damage according to the maximum stress value and maximum fatigue life.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the fatigue damage prediction method for key components of offshore photovoltaics according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the fatigue damage prediction method for key components of offshore photovoltaics according to any one of claims 1 to 7 by executing the executable instructions.

Images