Pipe truss structure fatigue analysis parameter optimization method and system based on deep learning

Abstract

The invention relates to the technical field of structure fatigue evaluation, in particular to a pipe truss structure fatigue analysis parameter optimization method and system based on deep learning, and the method comprises the following steps: constructing a deep learning proxy model fusing a multi-scale structure diagram encoder, a working condition parameter encoder and a damage dimension curve decoder; training the model by using a high-fidelity training data set; for the target truss structure and the load working condition, predicting a damage dimension relation curve through the model; determining the optimal dimension of a rain flow counting matrix by analyzing the convergence characteristic of the curve; and predicting a multi-working-condition damage value through a model, and screening out a dominant working condition based on a damage contribution percentage. According to the method, the deep learning agent model is used for replacing traditional iterative simulation, rapid optimization of key parameters in fatigue analysis is achieved, the efficiency and accuracy of fatigue evaluation of the large truss structure are remarkably improved, and the generalization ability of the model is improved by fusing the physical effect of a multi-scale structure chart encoder to capture key hotspots.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of structural fatigue evaluation, in particular to a pipe truss structure fatigue analysis parameter optimization method and system based on deep learning. BACKGROUND

[0002] Large pipe truss structures, such as wind towers, offshore platforms, etc., bear complex alternating loads such as wind and waves during long-term service, and fatigue damage is a key factor affecting their safety and service life. Currently, when engineering fatigue evaluation of such structures is performed, the following technical process is usually adopted: first, stress time history data of key parts of the structure are obtained through finite element simulation, then the rainflow counting method is used to convert the stress time history into a rainflow counting matrix, and finally the cumulative fatigue damage is calculated in combination with the S-N curve and the Miner criterion. S - N

[0003] However, in the above traditional evaluation method, the following defects exist: 1. The dimension of the rainflow counting matrix lacks scientific basis; the matrix dimension (i.e. the number of discrete intervals of load amplitude and mean value) directly affects the calculation accuracy of fatigue damage, and at present the dimension is mostly set by engineers according to experience or recommended values in specifications, which has great subjectivity; if the dimension is too low, the load cycle information will be lost and the damage calculation will be conservative; if the dimension is too high, it will significantly increase the data storage and calculation burden; in order to seek a reasonable dimension, the traditional method needs to repeatedly perform the complete fatigue simulation and calculation process for different dimensions, which is time-consuming and difficult to be widely applied in practical engineering. 2. The calculation efficiency of multi-condition analysis is low; according to the requirements of relevant specifications, fatigue evaluation needs to consider hundreds of design load conditions formed by combinations of wind speed, wind direction, running state, etc.; if full-process simulation and damage calculation are performed for each condition, the calculation cost will increase dramatically, which becomes the main bottleneck restricting the efficiency of structural optimization design and safety evaluation.

[0004] In summary, the traditional evaluation method relies on experience and lacks objective basis when determining the dimension of the rainflow counting matrix, and has the problem of low calculation efficiency when facing numerous design load conditions, resulting in low efficiency and insufficient reliability in the fatigue evaluation process. SUMMARY

[0005] The present application aims to provide a pipe truss structure fatigue analysis parameter optimization method and system based on deep learning to solve the technical problems pointed out in the background.

[0006] The present application is implemented by the following technical solution: a pipe truss structure fatigue analysis parameter optimization method based on deep learning, which is suitable for determining the optimal dimension of the rainflow counting matrix and screening design load conditions, including the following steps: ​The deep learning agent model comprises a multi-scale structure graph encoder, a working condition parameter encoder, and a damage dimension curve decoder. The multi-scale structure graph encoder is used to encode global truss topological information and local hot spot geometric information of a truss structure into a structure feature vector. The working condition parameter encoder is used to encode design load working condition parameters into a load feature vector. The damage dimension curve decoder is used to fuse the structure feature vector and the load feature vector, and output a damage dimension prediction curve vector. A high-fidelity training data set is obtained, and the deep learning agent model is trained using the high-fidelity training data set to obtain a trained agent model. For a target truss structure to be analyzed and a target design load working condition, the global truss topological information and the local hot spot geometric information of the target truss structure are encoded, and the design load working condition parameters of the target design load working condition are determined. The global truss topological information, the local hot spot geometric information, and the design load working condition parameters are input into the trained agent model to obtain a damage dimension prediction curve vector. The determination of the rainflow counting matrix dimension comprises: The optimal dimension of the rainflow counting matrix is determined by analyzing the convergence characteristics of the damage dimension prediction curve vector. The selection of the design load working condition comprises: The dominant working condition is determined by analyzing the damage contribution percentages of each design load working condition.

[0007] According to a preferred embodiment, the multi-scale structure graph encoder comprises: A global graph neural network module is used to encode the overall mechanical response characteristics contained in the global truss topological information to obtain a global feature vector. A local geometric encoder module is used to encode the stress concentration effect contained in the local hot spot geometric information to obtain a local feature vector. A fusion module is used to fuse the global feature vector and the local feature vector to obtain the structure feature vector.

[0008] According to a preferred embodiment, the damage dimension curve decoder is based on a Transformer decoder architecture, which comprises a set of learnable dimension query embeddings, the number of which N is the same as the number of preset rainflow counting dimensions, and each dimension query embedding corresponds to a preset rainflow counting dimension.

[0009] According to a preferred embodiment, the obtaining of the damage dimension prediction curve vector specifically comprises: receiving a context vector formed by the fusion of the structure feature vector and the load feature vector as memory, and processing in parallel through a multi-head attention mechanismN Each dimension query embedding is used, and the output corresponding to each dimension query embedding is mapped to a cumulative fatigue damage value through a shared regression head, resulting in a single output. N The damage dimension prediction curve vector.

[0010] According to a preferred embodiment, obtaining the high-fidelity training dataset includes: Create several parametric truss structure samples Operating Parameter Sample ; For each group of samples Perform high-fidelity physical simulation processing, including obtaining the original fatigue load time series through load simulation and establishing a multi-scale finite element analysis model to obtain the load hot spot stress curve; against N For each of the preset rainflow counting matrix dimensions, rainflow counting and fatigue damage accumulation calculation are performed to obtain the actual cumulative fatigue damage corresponding to each dimension. Based on the actual cumulative fatigue damage values, a damage dimension relationship curve vector is generated and paired with the corresponding samples to construct a high-fidelity training dataset.

[0011] According to a preferred embodiment, the operating condition parameter sample includes operating condition type, wind speed, wind seed, and inflow angle parameters.

[0012] According to a preferred embodiment, during the training process of the deep learning proxy model, the objective is to minimize the difference between the predicted cumulative fatigue damage value and the actual cumulative fatigue damage value. The expression of the objective function is as follows:

[0013] In the above formula, For the input sample, Labels for the damage dimension relationship curve vector. For high-fidelity training datasets, The first term represents the adjustment of the sensitivity of the convergence region. Weighting coefficients for each dimension Indicates the first The cumulative fatigue damage prediction value in each dimension Indicates the first The true value of cumulative fatigue damage in each dimension.

[0014] According to a preferred embodiment, determining the optimal dimension of the rainflow counting matrix includes: Set a convergence threshold; The relative rate of change of cumulative fatigue damage prediction values ​​between adjacent points on the damage dimension prediction curve is calculated using the following expression:

[0015] In the above formula, represents the relative change rate of the cumulative fatigue damage prediction value, represents the cumulative fatigue damage prediction value of the first dimension; determines the optimal dimension of the rainflow counting matrix based on the relative change rate of the cumulative fatigue damage prediction value , expressed as follows:

[0016] In the above formula, represents the optimal dimension of the rainflow counting matrix, represents the convergence threshold.

[0017] According to a preferred embodiment, the screening step of the design load case specifically includes: extracting the cumulative fatigue damage prediction value in the optimal dimension or the preset dimension from each of the damage dimension prediction curve vectors; calculating the damage contribution percentage of each design load case based on the cumulative fatigue damage prediction value; and determining the dominant case from each design load case according to the damage contribution percentage.

[0018] The present application also provides a deep learning-based tubular truss structure fatigue analysis parameter optimization system, which is used to execute the deep learning-based tubular truss structure fatigue analysis parameter optimization method as described above, and the system includes: a model construction module for constructing a deep learning agent model, the deep learning agent model including a multi-scale structure graph encoder, a working condition parameter encoder, and a damage dimension curve decoder, wherein the multi-scale structure graph encoder is used to encode the global truss topology information and the local hot spot geometric information of the truss structure into a structure feature vector, the working condition parameter encoder is used to encode the design load working condition parameters into a load feature vector, and the damage dimension curve decoder is used to fuse the structure feature vector and the load feature vector and output a damage dimension prediction curve vector; a model training module for obtaining a high-fidelity training data set and training the deep learning agent model using the high-fidelity training data set to obtain a trained agent model; a data acquisition module for determining the global truss topology information and the local hot spot geometric information coding of the target truss structure and the design load working condition parameters of the target design load working condition for the target truss structure to be analyzed; A prediction module is configured to input the global truss topology information, local hot spot geometry information coding and design load working condition parameters into a trained proxy model to obtain a damage dimension prediction curve vector; A first application module is configured to determine an optimal dimension of a rainflow counting matrix by analyzing the convergence characteristics of the damage dimension prediction curve vector. A second application module is configured to determine a dominant working condition by analyzing the damage contribution percentages of each design load working condition.

[0019] The technical scheme of the pipe truss structure fatigue analysis parameter optimization method and system based on deep learning provided by the present application has at least the following advantages and beneficial effects: (1) the present application converts the traditional simulation process requiring multiple iterations into a one-time model forward inference by constructing and training a deep learning proxy model, thereby achieving rapid completion of dimension optimization and working condition selection, greatly shortening the analysis period, and providing strong support for rapid iteration and optimization of engineering design; (2) the present application predicts a complete damage dimension relationship curve at one time and automatically determines the optimal dimension based on a preset convergence criterion, so that the dimension selection is changed from experience setting to data-driven convergence optimization, thereby significantly improving the accuracy and reliability of fatigue evaluation; (3) the present application uses the trained proxy model to predict the cumulative damage of each working condition in parallel, and quantifies the influence degree of each working condition through the damage contribution percentage, thereby quickly selecting one or more dominant working conditions with the largest contribution, which not only greatly reduces the number of working conditions that need to be analyzed in detail, but also ensures that fatigue evaluation is still focused on the most critical load conditions, thereby simplifying the analysis process; (4) the multi-scale structure graph encoder used in the present application combines global graph neural networks and local geometry encoders, which can simultaneously capture the overall mechanical properties and local stress concentration effects of the structure, and this design makes the model not limited to a specific topology or geometry, but applicable to pipe truss structures of different types and sizes, and has strong generalization ability, unlike a black box model for a single structure. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 The overall flowchart of the pipe truss structure fatigue analysis parameter optimization method provided for embodiment 1 of the present application is shown in the figure. Figure 2 The architecture diagram of the deep learning proxy model provided for embodiment 1 of the present application is shown in the figure. Figure 3 The high-fidelity training data set generation diagram provided for embodiment 1 of the present application is shown in the figure. Figure 4 The parameter optimization diagram provided for embodiment 1 of the present application is shown in the figure. Figure 5 The damage dimension prediction curve and optimal dimension determination diagram provided for embodiment 1 of the present application is shown in the figure. Figure 6 A schematic diagram of a dominant working condition screening process is provided for the embodiment 1 of the present application. Figure 7 A schematic diagram of a cumulative fatigue damage contribution percentage of each working condition is provided for the embodiment 1 of the present application. Figure 8 A structural block diagram of a tubular truss structure fatigue analysis parameter optimization system is provided for the embodiment 2 of the present application. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the accompanying drawings herein can be arranged and designed in various different configurations.

[0022] Embodiment 1 The embodiment of the present application provides a tubular truss structure fatigue analysis parameter optimization method based on deep learning, which is suitable for determining the optimal dimension of a rainflow counting matrix and screening design load working conditions, Figure 1 A schematic diagram of the overall process of the tubular truss structure fatigue analysis parameter optimization method is shown in Figure 1 The tubular truss structure fatigue analysis parameter optimization method includes the following steps: Step S1, constructing and training a deep learning agent model; In the present embodiment, this step aims to establish an agent model capable of quickly and accurately predicting damage dimension curves to replace high-fidelity physical simulation; specifically including: Step S101, model construction; First, a deep learning agent model as shown in Figure 2 is constructed, which is composed of two encoders and one decoder, respectively: Multi-scale structure graph encoder: for comprehensively capturing the mechanical characteristics of the truss structure; specifically, the multi-scale structure graph encoder further comprises a global graph neural network module, a local geometry encoder module, and a fusion module; wherein the global graph neural network module is used to take the entire tower tube rod topological structure (node coordinates, rod connection relationship) as input, learn the overall mechanical response characteristics of the structure through a multi-layer graph convolution network, and output a global feature vector; the local geometry encoder module focuses on stress concentration areas, such as pipe node welds, and inputs local geometric parameters of these hot spots, such as pipe diameter, wall thickness, chord and web angle, etc., encodes the local stress concentration effect through a multi-layer perceptron, and outputs a local feature vector; the fusion module combines the global and local feature vectors to form the final structure feature vector through splicing operation and the like. It should be noted that by fusing the global graph neural network and the local geometry encoder, the multi-scale structure graph encoder can simultaneously capture the overall mechanical characteristics and local stress concentration effect of the structure. This design makes the model not limited to a specific topology or geometric form, and can be applied to different types and sizes of pipe truss structures, and has strong generalization ability, rather than a black box model for a single structure.

[0023] Working condition parameter encoder: this part is a fully connected neural network; the input is a parameter vector of a specific design working condition, which in this embodiment includes: working condition type, average wind speed, wind seed and inflow angle, and the working condition parameter encoder is used to map these parameters into a load feature vector.

[0024] Damage dimension curve decoder: adopts a decoder architecture based on Transformer; the core is a set of learnable dimension query embeddings, the number of embeddings N corresponds to the number of dimensions of the rainflow counting matrix; the decoder receives a context vector generated by fusing the structure feature vector and the load feature vector as memory, and through a multi-head attention mechanism, each dimension query embedding interacts with the context vector in parallel to learn to focus on the features related to a specific dimension; finally, the output corresponding to each query embedding is mapped to a scalar through a shared regression head, i.e. the predicted cumulative fatigue damage value under that dimension; finally, the damage dimension curve decoder outputs a N vector of damage dimension prediction curves.

[0025] Step S102, high-fidelity training data set preparation; In order to train the deep learning agent model constructed in step S101, a high-fidelity data set needs to be prepared, as shown in Figure 3 , the specific process is as follows: Through parameterized modeling, a batch of truss structure samples with different geometric sizes and topological forms are generated ; at the same time, a batch of working condition parameter samples are generated by combining different working condition parameters ; For each group of samples Perform high-fidelity physical simulation processing, including obtaining original fatigue load time sequence through load simulation, and establishing a multi-scale finite element analysis model to obtain a load hot spot stress curve; For N A preset rainflow counting matrix dimension, respectively, perform rainflow counting and fatigue damage accumulation calculation, and obtain the real cumulative fatigue damage corresponding to each dimension; Based on the real cumulative fatigue damage value, generate a damage dimension relationship curve vector, and pair it with the corresponding sample to construct a high-fidelity training dataset.

[0026] Step S103, model training; Use the high-fidelity training dataset constructed in step S102 to supervise the training of the deep learning agent model constructed in step S101; In some embodiments of the present embodiment, during the training process of the deep learning agent model, the difference between the cumulative fatigue damage prediction value and the real value of the cumulative fatigue damage is minimized as the target, and the expression of the objective function is as follows:

[0027] In the above formula, is the input sample, is the damage dimension relationship curve vector label, is the high-fidelity training dataset, represents the weighting coefficient of the jth dimension for adjusting the sensitivity of the convergence area, represents the cumulative fatigue damage prediction value of the jth dimension, represents the real value of the cumulative fatigue damage of the jth dimension.

[0028] It should be noted that by constructing and training the deep learning agent model, the traditional iterative simulation process is changed to a one-time model forward inference, which can quickly complete dimension optimization and working condition screening, greatly shortening the analysis period and providing strong support for rapid iteration and optimization of engineering design.

[0029] Step S2, apply the trained agent model for parameter optimization; Referring to Figure 4 ​​​As shown, for the target truss structure to be analyzed and the target design load condition, firstly, the global truss topology information and local hotspot geometric information encoding of the target truss structure, as well as the design load condition parameters of the target design load condition, are determined; then, the global truss topology information, local hotspot geometric information encoding and design load condition parameters are input into the trained surrogate model to obtain the damage dimension prediction curve vector.

[0030] Regarding the determination of the dimensions of the rainflow counting matrix, in this specific embodiment, it is determined by analyzing the convergence characteristics of the damage dimension prediction curve vector. See [link to relevant documentation]. Figure 5 As shown, Figure 5 The first curve on the right corresponds to the damage dimension prediction curve under the DLC1.2 load condition, the second curve corresponds to the damage dimension prediction curve under the DLC2.4 load condition, and the third curve corresponds to the total damage dimension prediction curve for all load conditions. Figure 5 The prediction curves for each damage dimension clearly demonstrate the predicted cumulative fatigue damage values. With dimension Physical properties that increase but gradually decrease and tend to converge, and fatigue life as a function of dimension. The characteristic of gradually increasing with addition; the specific steps to determine the optimal dimension are as follows: First, set a convergence threshold; Then, the relative rate of change of cumulative fatigue damage prediction values ​​between adjacent dimension points on the damage dimension prediction curve is calculated, as shown in the following expression:

[0031] In the above formula, This represents the relative rate of change of the predicted cumulative fatigue damage. Indicates the first The cumulative fatigue damage prediction value in each dimension; Finally, based on the relative rate of change of the cumulative fatigue damage prediction value... The optimal dimension of the rainflow counting matrix is ​​determined by the following expression:

[0032] In the above formula, The optimal dimension for representing the rainflow counting matrix. This represents the convergence threshold. It is the threshold value relative to the rate of change of the cumulative fatigue damage prediction. First time less than the convergence threshold At times, for example, in dimensions hour, less than the convergence threshold If the curve has essentially converged at this point, then the dimension is considered to be... That is, the optimal dimension of the structure under such working conditions.

[0033] It should be noted that by predicting the complete damage dimension relationship curve at one time and automatically determining the optimal dimension based on the preset convergence criterion, the dimension selection is changed from empirical setting to data-driven convergence optimization, which significantly improves the accuracy and reliability of fatigue evaluation.

[0034] Regarding the screening of design load working conditions, in the embodiment, the dominant working condition is determined by analyzing the damage contribution percentage of each design load working condition, as shown in Figure 6 and Figure 7 The steps are as follows: First, from each of the damage dimension prediction curve vectors, the cumulative fatigue damage prediction value at the optimal dimension or the preset dimension is extracted, and the total damage is calculated, as follows:

[0035] In the above formula, represents the number of design load working conditions, represents the cumulative fatigue damage prediction value of the th design load working condition; Second, based on the cumulative fatigue damage prediction value, the damage contribution percentage of each design load working condition is calculated, as follows:

[0036] In the above formula, represents the damage contribution percentage of the th design load working condition; Finally, according to the damage contribution percentage, the dominant working condition is determined from each design load working condition, and the design load working condition with a damage contribution percentage greater than a preset screening threshold is determined as the dominant working condition.

[0037] As can be seen from Figure 7 , the damage contribution percentage of the normal power generation working condition DLC1.2 is greater than 95%, and the total contribution of all other working conditions is less than 5%. If the preset screening threshold is 95%, then since the damage contribution percentage of the normal power generation working condition DLC1.2 is greater than the preset screening threshold, the normal power generation working condition DLC1.2 is determined as the dominant working condition.

[0038] It should be noted that by using the trained surrogate model, the cumulative damage of each working condition can be predicted in parallel, and the influence degree of each working condition can be quantified by the damage contribution percentage, so that one or more dominant working conditions with the largest contribution can be quickly screened out. This method not only greatly reduces the number of working conditions that need to be analyzed in detail, but also ensures that fatigue evaluation is still focused on the most critical load conditions, achieving simplification of the analysis process.

[0039] Embodiment 2 Based on the technical solutions provided in Embodiment 1, an embodiment of the present application provides a deep learning-based pipe truss structure fatigue analysis parameter optimization system, which is used to execute the deep learning-based pipe truss structure fatigue analysis parameter optimization method as described in Embodiment 1, as shown in Figure 8 The system comprises: a model construction module, configured to construct a deep learning agent model, wherein the deep learning agent model comprises a multi-scale structure graph encoder, a working condition parameter encoder, and a damage dimension curve decoder, the multi-scale structure graph encoder is configured to encode global truss topological information and local hot spot geometric information of a truss structure into a structure feature vector, the working condition parameter encoder is configured to encode design load working condition parameters into a load feature vector, and the damage dimension curve decoder is configured to fuse the structure feature vector and the load feature vector and output a damage dimension prediction curve vector; a model training module, configured to obtain a high-fidelity training data set and train the deep learning agent model using the high-fidelity training data set to obtain a trained agent model; a data acquisition module, configured to determine global truss topological information and local hot spot geometric information coding of a target truss structure to be analyzed and design load working condition parameters of a target design load working condition; a prediction module, configured to input the global truss topological information, the local hot spot geometric information coding, and the design load working condition parameters into the trained agent model to obtain a damage dimension prediction curve vector; a first application module, configured to determine an optimal dimension of a rainflow counting matrix by analyzing a convergence characteristic of the damage dimension prediction curve vector; a second application module, configured to determine a dominant working condition by analyzing a damage contribution percentage of each design load working condition.

[0040] The functions and technical effects of each module of the deep learning-based pipe truss structure fatigue analysis parameter optimization system of the present embodiment are the same as those of the deep learning-based pipe truss structure fatigue analysis parameter optimization method, and will not be repeated here.

[0041] The above is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A deep learning-based parameter optimization method for fatigue analysis of tubular truss structures, suitable for determining the optimal dimension of a rainflow counting matrix and screening design load cases, characterized in that, The method comprises the following steps: constructing a deep learning agent model, the deep learning agent model comprising a multi-scale structure graph encoder, a working condition parameter encoder, and a damage dimension curve decoder, wherein the multi-scale structure graph encoder is used to encode global truss topological information and local hot spot geometric information of a truss structure into a structure feature vector, the working condition parameter encoder is used to encode design load working condition parameters into a load feature vector, and the damage dimension curve decoder is used to fuse the structure feature vector and the load feature vector and output a damage dimension prediction curve vector; obtaining a high-fidelity training data set and training the deep learning agent model by using the high-fidelity training data set to obtain a trained agent model; for a target truss structure to be analyzed and a target design load working condition, determining global truss topological information and local hot spot geometric information coding of the target truss structure and design load working condition parameters of the target design load working condition; inputting the global truss topological information, local hot spot geometric information coding, and design load working condition parameters into the trained agent model to obtain a damage dimension prediction curve vector; the step of determining the dimension of the rainflow counting matrix comprises: determining the optimal dimension of the rainflow counting matrix by analyzing the convergence characteristics of the damage dimension prediction curve vector; the step of screening the design load working condition comprises: determining a dominant working condition by analyzing the damage contribution percentages of each design load working condition. 2.The deep learning-based parameter optimization method for tube truss structure fatigue analysis according to claim 1, wherein, The multi-scale structure graph encoder comprises: a global graph neural network module for encoding overall mechanical response characteristics contained in the global truss topological information to obtain a global feature vector, a local geometric encoder module for encoding stress concentration effects contained in the local hot spot geometric information to obtain a local feature vector; a fusion module for fusing the global feature vector and the local feature vector to obtain the structure feature vector. 3.The deep learning-based parameter optimization method for tubular truss structure fatigue analysis according to claim 1, wherein, The damage dimension curve decoder is based on a Transformer decoder architecture, including a set of learnable dimension query embeddings, the number of which N Each of the dimension query embeddings corresponds to a preset rainflow count dimension, which is the same as a preset number of rainflow count dimensions. 4.The deep learning-based parameter optimization method for tube-truss structure fatigue analysis according to claim 3, wherein, The damage dimension prediction curve vector is obtained, specifically comprising: receiving a context vector formed by fusing the structure feature vector and the load feature vector as memory, processing a plurality of dimension query embeddings in parallel through a multi-head attention mechanism, and mapping each dimension query embedding corresponding output to an accumulated fatigue damage value through a shared regression head to output one N dimensional damage dimension prediction curve vector. N dimensional damage dimension prediction curve vector. 5.The deep learning-based parameter optimization method for tube-truss structure fatigue analysis according to claim 1, wherein, The acquisition of the high-fidelity training data set comprises: creating a number of parameterized truss structure samples with working condition parameter samples ; For each set of samples High-fidelity physics simulation process is performed, including obtaining original fatigue load time series through load simulation, and establishing a multi-scale finite element analysis model to obtain load hot spot stress curve; For N a preset rain flow counting matrix dimension, respectively, the rain flow counting and fatigue damage accumulation calculation are performed to obtain the real cumulative fatigue damage corresponding to each dimension; generating a damage dimension relationship curve vector based on the true cumulative fatigue damage value, pairing the damage dimension relationship curve vector with a corresponding sample, and constructing a high-fidelity training data set. 6.The deep learning-based parameter optimization method for tube-truss structure fatigue analysis according to claim 5, wherein, The working condition parameter sample comprises a working condition type, a wind speed, a wind seed, and an inflow angle parameter. 7.The deep learning-based parameter optimization method for tubular truss structure fatigue analysis according to claim 1, wherein, In the training process of the deep learning agent model, the difference between the cumulative fatigue damage prediction value and the true value is minimized as the target, and the expression of the objective function is as follows: In the above formula, is the input sample, is the damage dimension relationship curve vector label, is the high-fidelity training data set, represents the weight coefficient of the first dimension adjusting the convergence area sensitivity, represents the cumulative fatigue damage prediction value of the first dimension, represents the cumulative fatigue damage true value of the first dimension. 8.The deep learning-based parameter optimization method for tubular truss structure fatigue analysis according to claim 1, wherein, The determination of the optimal dimension of the rainflow counting matrix comprises: setting a convergence threshold; calculating the relative change rate of the cumulative fatigue damage prediction value between adjacent dimension points on the damage dimension prediction curve, and the expression is as follows: In the above formula, represents the relative change rate of the cumulative fatigue damage prediction value, represents the cumulative fatigue damage prediction value of the first dimension. based on the relative change rate of the accumulated fatigue damage prediction value determining the optimal dimension of the rainflow counting matrix, expressed as follows: In the above formula, represents the optimal dimension of the rainflow counting matrix, represents the convergence threshold. 9.The deep learning-based parameter optimization method for tubular truss structure fatigue analysis according to claim 1, wherein, The screening step of the design load working condition specifically comprises: extracting the cumulative fatigue damage prediction value at the optimal dimension or a preset dimension from each damage dimension prediction curve vector; calculating the damage contribution percentage of each design load working condition based on the cumulative fatigue damage prediction value; and determining a dominant working condition from each design load working condition according to the damage contribution percentage.

10. A deep learning-based parameter optimization system for fatigue analysis of a tubular truss structure, characterized by, The system is used to perform the deep learning-based pipe truss structure fatigue analysis parameter optimization method according to any one of claims 1 to 9, and the system comprises: The model construction module is configured to construct a deep learning agent model, which comprises a multi-scale structure graph encoder, a working condition parameter encoder, and a damage dimension curve decoder. The model training module is configured to obtain a high-fidelity training data set and train the deep learning agent model using the high-fidelity training data set to obtain a trained agent model. The data acquisition module is configured to determine the global truss topology information and the local hot spot geometric information of a target truss structure to be analyzed and the design load working condition parameters of a target design load working condition. The prediction module is configured to input the global truss topology information, the local hot spot geometric information, and the design load working condition parameters into the trained agent model to obtain a damage dimension prediction curve vector. The first application module is configured to determine the optimal dimension of a rain flow counting matrix by analyzing the convergence characteristics of the damage dimension prediction curve vector. The second application module is configured to determine a dominant working condition by analyzing the damage contribution percentages of each design load working condition.

Images