Dynamic response analysis method for elastic supporting structure of gas turbine cylinder

Abstract

The invention relates to a dynamic response analysis method for an elastic supporting structure of a gas turbine cylinder, and the method comprises the steps: generating a finite element simulation result of the elastic supporting structure of the gas turbine cylinder based on at least one of an isotropic loss factor, a structural size, an elastic modulus and an acting load of the elastic supporting structure of the gas turbine cylinder; constructing a firefly optimization algorithm-back propagation FA-BP neural network model; training an FA-BP neural network model by using the training set; and evaluating the trained FA-BP neural network model, and generating a dynamic response result of the gas turbine cylinder elastic support structure after an evaluation result meets a preset condition. According to the embodiment of the invention, training and prediction of the dynamic analysis model of the elastic support structure can be realized, a rapid iteration method is provided for design optimization, the calculation efficiency of dynamic simulation of the elastic support in an iteration design process is improved, and a dynamic simulation method considering both efficiency and precision is realized.

Description

Technical Field

[0001] The present application relates to the technical field of gas turbines, and in particular to a method for analyzing the dynamic response of an elastic support structure of a gas turbine cylinder. Background Art

[0002] Heavy-duty gas turbines usually operate under extremely harsh working conditions such as high temperature, high pressure, high speed, and thermal-fluid-solid multi-field coupling. Among them, the cylinder elastic support plays a vital role in the gas turbine system. The main function of the elastic support structure is to ensure that the cylinder can be stably fixed on the foundation during operation, while absorbing and isolating the vibration generated by the operation of the gas turbine. It can effectively reduce the transmission of vibration generated during the operation of the gas turbine to the foundation, thereby protecting the foundation structure from damage and reducing the vibration impact on the surrounding environment. Secondly, the elastic support helps to maintain the precise position of the cylinder and prevent coaxiality deviation caused by vibration, which is directly related to the efficiency and performance of the gas turbine. Furthermore, by absorbing vibration, the elastic support can also reduce the wear of the internal components of the cylinder and extend the service life of the gas turbine. Finally, a good cylinder and foundation support system helps to reduce the noise level, improve the working environment, and meet environmental protection requirements. It can be seen that the elastic support between the cylinder and the foundation is a key factor in the stable, efficient and safe operation of the gas turbine, and its design and application must be given full attention. Therefore, the dynamic characteristics analysis of the cylinder elastic support in the design process is very important.

[0003] For structural optimization, the prediction of dynamic response is an important factor affecting structural optimization. On the one hand, the accuracy of predicting dynamic response is the basis of optimization. Overestimation or underestimation of dynamic response will lead to safety or performance loss. In different stages of structural design, experimental methods or numerical calculation methods based on finite elements are usually used. The effectiveness of these methods has been widely verified, ensuring the accuracy of dynamic response. On the other hand, the efficiency of dynamic response prediction determines the implementation cost of the optimization algorithm. Generally speaking, a large amount of data needs to be obtained through experiments or calculations to estimate the objective function. The larger the amount of data, the more accurate the estimation of the objective function, which means that all parameter values ​​that meet the constraints need to be traversed. When the number of design parameters is high, the existence of dimensionality disaster causes this traversal to be performed tens of thousands of times or more. For time considerations, this is impossible for experiments. For numerical calculation methods based on finite elements, such a huge number of examples is also difficult to achieve. In addition to the huge amount of calculation and calculation time requirements, meshing also brings huge labor costs. This makes the data obtained by these methods insufficient to achieve the accurate implementation of the optimization algorithm within a relatively short development cycle. Therefore, an efficient, fast and accurate dynamic response prediction method is of great significance for structural optimization. Summary of the invention

[0004] The present application provides a method for analyzing the dynamic response of an elastic support structure of a gas turbine cylinder to solve the problem in related technologies that the accuracy of the dynamic response and the efficiency of the dynamic response prediction are low, and it is difficult to accurately implement the optimization algorithm within the development cycle.

[0005] The first aspect of the present application provides a method for analyzing the dynamic response of a gas turbine cylinder elastic support structure, comprising the following steps: generating a finite element simulation result of the gas turbine cylinder elastic support structure based on at least one of the isotropic loss factor, structural size, elastic modulus and applied load of the gas turbine cylinder elastic support structure, and extracting the dynamic response output data of a target machine learning model from the finite element simulation result; constructing a firefly optimization algorithm-back propagation FA-BP neural network model based on the dynamic response output data and according to a plurality of parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter; training the FA-BP neural network model using a training set to obtain a trained FA-BP neural network model; evaluating the trained FA-BP neural network model based on at least one evaluation index of the mean absolute percentage error and the determination coefficient to obtain an evaluation result, and generating a dynamic response result of the gas turbine cylinder elastic support structure after the evaluation result meets a preset condition.

[0006] Optionally, in one embodiment of the present application, extracting the output result of the preset machine learning model from the finite element simulation results includes: extracting stress values ​​that meet preset maximum conditions among multiple three-dimensional intercept points, and predicting multi-order natural frequencies of the gas turbine cylinder elastic support structure; determining the output result of the preset machine learning model based on the stress values ​​that meet the preset maximum conditions among the multiple three-dimensional intercept points and the multi-order natural frequencies of the gas turbine cylinder elastic support structure.

[0007] Optionally, in one embodiment of the present application, the firefly optimization algorithm-back propagation FA-BP neural network model is constructed according to multiple parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter, including: normalizing the data in the data set to obtain processed data; based on the processed data, generating input nodes according to the parameters of the gas turbine cylinder elastic support structure and the at least one external load parameter, and generating output nodes according to the stress values ​​that meet the preset maximum conditions in the multiple three-dimensional intercept points and the multi-order natural frequencies; and constructing the FA-BP neural network model based on the input nodes and the output nodes.

[0008] Optionally, in one embodiment of the present application, the calculation formula of the mutual attraction in the firefly optimization algorithm-back propagation FA-BP neural network model is:

[0009]

[0010] Where β0 is r ij =0 when the initial attraction, γ is the light absorption coefficient, r ij is the Euclidean distance between individual fireflies;

[0011] The calculation formula of the Euclidean distance between the fireflies is:

[0012]

[0013] Among them, x id represents the position of firefly i in d-dimensional space, x jd represents the position of firefly j in d-dimensional space, and D represents D-dimensional space;

[0014] The firefly position update formula is:

[0015]

[0016] Among them, x j is the position of the firefly j with lower brightness, rand() is the random perturbation term, α is the step size factor, and t is the number of iterations.

[0017] Optionally, in one embodiment of the present application, the calculation formula of the mean absolute percentage error is:

[0018]

[0019] Among them, N is the number of data, t i is the true value, y i is the predicted value;

[0020] The calculation formula of the determination coefficient is:

[0021]

[0022] Where N is the number of data, y i is the true value, y i is the predicted value, is the mean of all true values.

[0023] The second aspect of the present application provides a dynamic response analysis device for a gas turbine cylinder elastic support structure, including: an extraction module, which is used to generate a finite element simulation result of the gas turbine cylinder elastic support structure based on at least one of the isotropic loss factor, structural size, elastic modulus and applied load of the gas turbine cylinder elastic support structure, and extract the dynamic response output data of the target machine learning model from the finite element simulation result; a construction module, which is used to construct a firefly optimization algorithm-back propagation FA-BP neural network model based on the dynamic response output data according to multiple parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter; a training module, which is used to train the FA-BP neural network model using a training set to obtain a trained FA-BP neural network model; an evaluation module, which is used to evaluate the trained FA-BP neural network model based on at least one evaluation index of the mean absolute percentage error and the determination coefficient to obtain an evaluation result, and generate the dynamic response result of the gas turbine cylinder elastic support structure after the evaluation result meets a preset condition.

[0024] Optionally, in one embodiment of the present application, the extraction module includes: an extraction unit, used to extract stress values ​​that meet the preset maximum conditions among multiple three-dimensional intercept points, and predict the multi-order natural frequencies of the gas turbine cylinder elastic support structure; a determination unit, used to determine the output result of the preset machine learning model based on the stress values ​​that meet the preset maximum conditions among the multiple three-dimensional intercept points and the multi-order natural frequencies of the gas turbine cylinder elastic support structure.

[0025] Optionally, in one embodiment of the present application, the construction module includes: a processing unit, used to normalize the data in the data set to obtain processed data; a generation unit, used to generate an input node based on the processed data, according to the parameters of the gas turbine cylinder elastic support structure and the at least one external load parameter, and generate an output node based on the stress values ​​that meet the preset maximum conditions in the multiple three-dimensional intercept points and the multi-order natural frequencies; a construction unit, used to construct the FA-BP neural network model based on the input nodes and the output nodes.

[0026] Optionally, in one embodiment of the present application, the calculation formula of the mutual attraction in the firefly optimization algorithm-back propagation FA-BP neural network model is:

[0027]

[0028] Where β0 is t ij =0 when the initial attraction, γ is the light absorption coefficient, r ij is the Euclidean distance between individual fireflies;

[0029] The calculation formula of the Euclidean distance between the fireflies is:

[0030]

[0031] Among them, x id represents the position of firefly i in d-dimensional space, x jd represents the position of firefly j in d-dimensional space, and D represents D-dimensional space;

[0032] The firefly position update formula is:

[0033]

[0034] Among them, x j is the position of the firefly j with lower brightness, rand() is the random perturbation term, α is the step size factor, and t is the number of iterations.

[0035] Optionally, in one embodiment of the present application, the calculation formula of the mean absolute percentage error is:

[0036]

[0037] Among them, N is the number of data, t i is the true value, y i is the predicted value;

[0038] The calculation formula of the determination coefficient is:

[0039]

[0040] Wherein, N is the number of data, t i is the true value, y i is the predicted value, is the mean of all true values.

[0041] A third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for analyzing the dynamic response of a gas turbine cylinder elastic support structure as described in the above embodiment.

[0042] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for analyzing the dynamic response of a gas turbine cylinder elastic support structure.

[0043] A fifth aspect of the present application provides a computer program product, which stores a computer program that, when executed by a processor, implements the above-mentioned method for analyzing the dynamic response of a gas turbine cylinder elastic support structure.

[0044] The embodiments of the present application can utilize artificial intelligence technology to realize the training and prediction of the dynamic analysis model of the elastic support structure, provide a fast iteration method for design optimization, improve the computational efficiency of the dynamic simulation of the elastic support during the iterative design process, and realize a dynamic simulation method that takes both efficiency and accuracy into consideration. Thus, the problems in the related art such as the low accuracy of the dynamic response and the low efficiency of the dynamic response prediction, and the difficulty in completing the accurate implementation of the optimization algorithm within the development cycle are solved.

[0045] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0047] Figure 1 A flowchart of a method for analyzing the dynamic response of a gas turbine cylinder elastic support structure according to an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a variable size of a cylinder elastic support according to an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a three-dimensional cut point in a cylinder elastic support according to an embodiment of the present application;

[0050] FIG4( a ) is a schematic diagram of maximum stress at a three-dimensional interception point 1 according to an embodiment of the present application;

[0051] FIG4( b ) is a schematic diagram of the maximum stress at a three-dimensional interception point 2 according to an embodiment of the present application;

[0052] FIG4( c ) is a schematic diagram of the maximum stress at a three-dimensional interception point 2 according to an embodiment of the present application;

[0053] FIG4( d ) is a schematic diagram of the first-order natural frequency according to an embodiment of the present application;

[0054] FIG4( e ) is a schematic diagram of the second-order natural frequency according to an embodiment of the present application;

[0055] FIG4( f) is a schematic diagram of the third-order natural frequency according to an embodiment of the present application;

[0056] FIG4( g) is a schematic diagram of the 4th order natural frequency according to an embodiment of the present application;

[0057] FIG4( h) is a schematic diagram of the fifth-order natural frequency according to an embodiment of the present application;

[0058] Figure 5 The present invention is a flow chart of a method for analyzing dynamic characteristics of gas turbine cylinder elastic support based on FA-BP neural network according to an embodiment of the present application;

[0059] Figure 6 It is a structural schematic diagram of a dynamic response analysis device for a gas turbine cylinder elastic support structure provided according to an embodiment of the present application;

[0060] Figure 7 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0061] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0062] The following describes a method for analyzing the dynamic response of an elastic support structure of a gas turbine cylinder according to an embodiment of the present application with reference to the accompanying drawings. In view of the problem that the accuracy of the dynamic response and the efficiency of the dynamic response prediction in the related technologies mentioned in the above background technology are low, and it is difficult to accurately implement the optimization algorithm within the development cycle, the present application provides a method for analyzing the dynamic response of an elastic support structure of a gas turbine cylinder. In this method, artificial intelligence technology can be used to realize the training and prediction of the dynamic analysis model of the elastic support structure, provide a fast iteration method for design optimization, improve the computational efficiency of the elastic support dynamic simulation during the iterative design process, and realize a dynamic simulation method that takes both efficiency and accuracy into account. As a result, the problems in the related technologies, such as the accuracy of the dynamic response and the efficiency of the dynamic response prediction are low, and it is difficult to accurately implement the optimization algorithm within the development cycle, are solved.

[0063] Specifically, Figure 1 A schematic flow chart of a method for analyzing the dynamic response of a gas turbine cylinder elastic support structure provided in an embodiment of the present application.

[0064] like Figure 1 As shown, the dynamic response analysis method of the gas turbine cylinder elastic support structure includes the following steps:

[0065] In step S101, based on at least one of the isotropic loss factor, structural size, elastic modulus and applied load of the gas turbine cylinder elastic support structure, a finite element simulation result of the gas turbine cylinder elastic support structure is generated, and the dynamic response output data of the target machine learning model is extracted from the finite element simulation result.

[0066] It is understandable that machine learning is gaining more and more applications in the field of structural optimization. After obtaining a certain amount of data through finite element calculations or experiments, a black box mathematical model can be used to approximate the real physical model based on the data to describe the relationship between parameters and dynamic responses. In the subsequent parameter traversal process, the dynamic response value can be obtained only through function calculation, which greatly reduces the traversal cost.

[0067] During the actual implementation process, for the structural type of the gas turbine cylinder elastic support model, the embodiment of the present application can obtain the finite element simulation results of the gas turbine cylinder elastic support structure by changing the structural isotropic loss factor, changing the structural size, changing the elastic modulus, changing the applied load, etc. Similar to the machine learning model of the rotor, the simulation analysis model of the machine learning model is obtained through pre-training to realize the prediction of the simulation results under different parameters of the cylinder elastic support structure.

[0068] From the perspective of method verification, in order to generate a large amount of training data, a static load loading method is used to obtain the load response of the cylinder elastic support structure. The variable structural parameter data of the cylinder elastic support include the thickness of plate 1 and the thickness of plate 2 ( Figure 2 ), isotropic loss factor, elastic modulus and applied load. The input parameters have a total of 5-dimensional input parameter space. In each dimension, different numbers of parameter values ​​are taken at equal intervals within a certain parameter floating range, generating a total of 5×5×10 3 The parameter grid of Table 1 is a list of the parameters of the cylinder elastic support structure, as shown in Table 1:

[0069] Table 1

[0070]

[0071]

[0072] Optionally, in one embodiment of the present application, the output results of the preset machine learning model are extracted from the finite element simulation results, including: extracting stress values ​​that meet preset maximum conditions among multiple three-dimensional intercept points, and predicting multi-order natural frequencies of the gas turbine cylinder elastic support structure; based on the stress values ​​that meet preset maximum conditions among multiple three-dimensional intercept points and the multi-order natural frequencies of the gas turbine cylinder elastic support structure, determining the output results of the preset machine learning model.

[0073] It can be understood that in the embodiment of the present application, the stress value that meets the preset maximum condition can be the maximum stress value.

[0074] In order to obtain the main force conditions and simulation analysis models at different positions, the embodiment of the present application also selects a total of 3 three-dimensional intercept points for prediction at different positions, such as Figure 3 As shown in Figure 3 As shown. After the simulation is completed, the maximum stress values ​​at these three-dimensional cutoff points during the simulation time are extracted, and these variables will be used as the output values ​​of the machine learning model. In addition, the machine learning model is used to predict the first five natural frequencies of the cylinder elastic support structure.

[0075] In summary, the output values ​​of the machine learning model proposed in this application total 8 categories, namely: the maximum stress at three-dimensional intercept point 1, the maximum stress at three-dimensional intercept point 2, the maximum stress at three-dimensional intercept point 3, the first-order natural frequency, the second-order natural frequency, the third-order natural frequency, the fourth-order natural frequency, and the fifth-order natural frequency. Figure 4(a) to Figure 4(h) shown.

[0076] It should be noted that the preset maximum condition can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0077] In step S102, based on the dynamic response output data, a firefly optimization algorithm-back propagation FA-BP neural network model is constructed according to a plurality of parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter.

[0078] In the actual implementation process, the embodiment of the present application can construct a firefly optimization algorithm-backward propagation FA-BP neural network model based on the dynamic response output data, according to multiple parameters characterizing the elastic support structure of the gas turbine cylinder and at least one external load parameter. Among them, the embodiment of the present application adopts 5 parameters characterizing the elastic support configuration of the cylinder and 1 external load parameter, that is, the input of the FA-BP neural network model is 6 parameters, so 6 input nodes are set. The hidden layer nodes are based on the empirical formula and trial and error method, wherein m and n are the number of neurons in the input layer and the output layer respectively. a is a positive integer between 1 and 10. The present invention sets the hidden layer nodes to 5. The output is 1 node.

[0079] Optionally, in one embodiment of the present application, a firefly optimization algorithm-back propagation FA-BP neural network model is constructed based on multiple parameters characterizing the elastic support structure of the gas turbine cylinder and at least one external load parameter, including: normalizing the data in the data set to obtain processed data; based on the processed data, generating input nodes according to the parameters of the elastic support structure of the gas turbine cylinder and at least one external load parameter, and generating output nodes according to the stress values ​​that meet the preset maximum conditions in multiple three-dimensional intercept points and the multi-order natural frequencies; and constructing the FA-BP neural network model based on the input nodes and the output nodes.

[0080] As a possible implementation method, the network in the embodiment of the present application adopts Sigmoid function as the activation function, and in order to make the data set within the activation function value range, the data is normalized to obtain the processed data. During the operation of the FA-BP network, the size of the learning rate can affect the stability of the network. After step-by-step experiments, the learning rate is set to 0.001. The number of training times is set to 1000. The target error is set to 0.00001. The learning function is Trainlm.

[0081] This application uses the firefly algorithm (FA) to optimize the network weights and thresholds, enhance the robustness of the network, and improve the prediction performance. FA is one of the popular algorithms in the field of swarm intelligence algorithms. It is inspired by how fireflies signal each other through flickering light to attract partners or warn potential predators. In order to build the search model of FA, there are three idealized rules. First, fireflies are not gender-specific, and they attract each other only considering the brightness of individual light. Second, attraction is proportional to the brightness of the light and inversely proportional to the distance between individuals. Third, the brightness of the firefly is determined by the numerical value of the objective function to be optimized. For this algorithm, each firefly represents a solution to the problem. The brightness of a firefly represents the fitness of its position. The higher the brightness, the better the position of the firefly in the solution space. Adjust the position and update the data by brightness comparison to obtain the optimal solution to the problem.

[0082] Assume that the position of firefly i in D-dimensional space is x i =(x i1 ,x i2 ,…,x iD ). Then, the brightness of the firefly is equal to the function value at that position, denoted as F i =f(x i ). If the brightness of firefly i is higher than that of firefly j, then firefly j will be attracted to firefly i.

[0083] Optionally, in one embodiment of the present application, the calculation formula of the mutual attraction in the firefly optimization algorithm-back propagation FA-BP neural network model is:

[0084]

[0085] Where β0 is r ij =0 when the initial attraction, γ is the light absorption coefficient, r ij is the Euclidean distance between individual fireflies;

[0086] The calculation formula of the Euclidean distance between individual fireflies is:

[0087]

[0088] Among them, x id represents the position of firefly i in d-dimensional space, x jd represents the position of firefly j in d-dimensional space, and D represents D-dimensional space;

[0089] During the calculation process, the firefly position update formula is:

[0090]

[0091] Among them, x j is the position of the firefly j with lower brightness, rand() is a random perturbation term, i.e., a Gaussian random number; α is the step size factor, which can be adjusted according to the pseudo-time step number in each iteration, so that the algorithm can balance between global search and local search during the search process; t is the number of iterations. Table 2 is the parameter setting table of the FA algorithm, where the relevant parameters of the firefly algorithm are shown in Table 2:

[0092] Table 2

[0093] Parameters Value Number of fireflies 20 Pseudo time steps 50 α 0.25 β 0.2 γ 1

[0094] In step S103, the FA-BP neural network model is trained using the training set to obtain a trained FA-BP neural network model.

[0095] In the actual implementation process, the embodiment of the present application can divide the data set into a training set, a validation set, and a test set by generating random sampling without replacement from the total data set, with a division ratio of 0.6, 0.2, and 0.2. The training set is used to train the model, and the FA-BP neural network model is trained using the training set to obtain the trained FA-BP neural network model, which contains 15,000 samples, the validation set is used to select model hyperparameters, with a total of 5,000 samples, and the test set is used for the final evaluation of the model effect, with a total of 5,000 samples.

[0096] The embodiment of the present application utilizes artificial intelligence technology to realize the training and prediction of the dynamic analysis model of the elastic support structure, provide a fast iteration method for design optimization, improve the computational efficiency of the elastic support dynamic simulation during the iterative design process, and realize a dynamic simulation method that takes into account both efficiency and accuracy.

[0097] In step S104, based on at least one evaluation index of the mean absolute percentage error and the determination coefficient, the trained FA-BP neural network model is evaluated to obtain an evaluation result, and after the evaluation result meets the preset conditions, the dynamic response result of the gas turbine cylinder elastic support structure is generated.

[0098] Specifically, this application designs 25,000 different cylinder elastic support configurations through different combinations of parameters and changes in size, of which 20,000 groups are used as training sets and validation sets for the network, and the remaining 5,000 groups are used as test sets for the network. In order to verify the effectiveness of the proposed network prediction, this application evaluates the trained FA-BP neural network model based on at least one evaluation indicator of the mean absolute percentage error and the coefficient of determination to obtain the evaluation results. Due to the large difference in the magnitude of the predicted parameters, the mean absolute percentage error (MAPE) and the coefficient of determination (R 2 ) for evaluation.

[0099] In one embodiment of the present application, MAPE is generally expressed in the form of a percentage. It can not only measure the error between the predicted value and the true value, but also consider the ratio of the error to the true value. The calculation formula of the mean absolute percentage error is:

[0100]

[0101] Among them, N is the number of data, t i is the true value, y i is the predicted value;

[0102] R 2 Can judge the fitness of the network. 2 The larger the value, the higher the degree of explanation of the independent variable on the dependent variable, and the higher the percentage of the change caused by the independent variable in the total change. This means that the observation points are denser near the regression line. The calculation formula of the determination coefficient is:

[0103]

[0104] Among them, N is the number of data, t i is the true value, y i is the predicted value, is the mean of all true values.

[0105] The embodiment of the present application relates to a simplified and efficient method for predicting gas turbine dynamic response parameters, which solves the problems of large calculation scale, long iteration process duration and large calculation workload in the dynamic analysis process of gas turbine cylinder elastic support.

[0106] Specifically, the working principle of a dynamic response analysis method for a gas turbine cylinder elastic support structure in an embodiment of the present application is described in detail with a specific embodiment.

[0107] Example:

[0108] exist Figure 2 The present invention is verified in the elastic support structure of the gas turbine cylinder shown in FIG. The prediction results of the proposed FA-BP model are shown in FIG. Figure 4(a) to Figure 4(h) As shown in the figure, the prediction results of 5000 test sets are shown. Since the natural frequency is only affected by the size and elastic modulus during the simulation, the training set and the validation set are 250 in total, and the test set is 50. Comparing the prediction results with the expected results, it can be seen that the overall prediction results are relatively close to the real data. The proposed FA-BP network has a high degree of fit and a small error, which can be used as an effective tool for predicting the dynamic response of the cylinder elastic support.

[0109] In addition, this application introduces MAPE and R 2 Two types of parameters quantitatively evaluate the prediction performance of FA-BP network. The specific results are shown in Table 3. It can be seen that R 2 All of them are higher than 99%, indicating that the FA-BP model has a good fitting degree and a high quality. MAPE has a low value, which means that the prediction results of the FA-BP model deviate little from the true value and have a high prediction performance.

[0110] Table 3

[0111] MAPE <![CDATA[R 2 ]]> 3D Intercept Point 1 0.056252951 0.997324685 3D Intercept Point 2 0.045319823 0.999242074 3D Intercept Point 3 0.001092034 0.999998059 1st natural frequency 0.005064654 0.999954379 Second order natural frequency 0.006589843 0.999941106 The third natural frequency 0.002106843 0.999999053 4th natural frequency 0.002071067 0.999783146 5th natural frequency 0.003655218 0.99964841

[0112] like Figure 5 As shown, the embodiment of the present application may include the following steps:

[0113] Step S501: construct elastic support models of gas turbine cylinders of different configurations.

[0114] Step S502: Isotropic loss factor, structural dimensions, elastic modulus and applied load.

[0115] Step S503: Finite element simulation.

[0116] Step S504: Outputting the dynamic responses of the cylinder elastic supports with different configurations.

[0117] Step S505: FA-BP neural network model.

[0118] Step S506: New configuration parameters.

[0119] Step S507: Dynamic response prediction.

[0120] Step S508: A high-precision and high-efficiency gas turbine cylinder elastic support dynamic response analysis method.

[0121] According to the dynamic response analysis method of the gas turbine cylinder elastic support structure proposed in the embodiment of the present application, artificial intelligence technology can be used to realize the training and prediction of the dynamic analysis model of the elastic support structure, provide a fast iteration method for design optimization, improve the computational efficiency of the elastic support dynamic simulation in the iterative design process, and realize a dynamic simulation method that takes both efficiency and accuracy into consideration. This solves the problem in the related technology that the accuracy of the dynamic response and the efficiency of the dynamic response prediction are low, and it is difficult to complete the accurate implementation of the optimization algorithm within the development cycle.

[0122] Next, a dynamic response analysis device for a gas turbine cylinder elastic support structure proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0123] Figure 6 It is a structural schematic diagram of a dynamic response analysis device for a gas turbine cylinder elastic support structure according to an embodiment of the present application.

[0124] like Figure 6 As shown, the dynamic response analysis device 10 of the gas turbine cylinder elastic support structure includes: an extraction module 100, a construction module 200, a training module 300 and an evaluation module 400.

[0125] Specifically, the extraction module 100 is used to generate finite element simulation results of the gas turbine cylinder elastic support structure based on at least one of the isotropic loss factor, structural size, elastic modulus and applied load of the gas turbine cylinder elastic support structure, and extract the dynamic response output data of the target machine learning model from the finite element simulation results.

[0126] The construction module 200 is used to construct a firefly optimization algorithm-back propagation FA-BP neural network model based on the dynamic response output data, according to multiple parameters characterizing the elastic support structure of the gas turbine cylinder and at least one external load parameter.

[0127] The training module 300 is used to train the FA-BP neural network model using the training set to obtain the trained FA-BP neural network model.

[0128] The evaluation module 400 is used to evaluate the trained FA-BP neural network model based on at least one evaluation index of the mean absolute percentage error and the determination coefficient, obtain an evaluation result, and generate a dynamic response result of the gas turbine cylinder elastic support structure after the evaluation result meets the preset conditions.

[0129] Optionally, in one embodiment of the present application, the extraction module 100 includes: an extraction unit and a determination unit.

[0130] Among them, the extraction unit is used to extract the stress values ​​that meet the preset maximum conditions in multiple three-dimensional intercept points, and predict the multi-order natural frequencies of the gas turbine cylinder elastic support structure.

[0131] A determination unit is used to determine the output result of a preset machine learning model based on stress values ​​that meet preset maximum conditions in multiple three-dimensional intercept points and multi-order natural frequencies of the gas turbine cylinder elastic support structure.

[0132] Optionally, in one embodiment of the present application, the construction module 200 includes: a processing unit, a generating unit and a construction unit.

[0133] The processing unit is used to normalize the data in the data set to obtain processed data.

[0134] A generating unit is used to generate input nodes based on the processed data according to the parameters of the gas turbine cylinder elastic support structure and at least one external load parameter, and to generate output nodes according to the stress values ​​and multi-order natural frequencies that meet the preset maximum conditions in multiple three-dimensional intercept points.

[0135] The construction unit is used to construct a FA-BP neural network model based on input nodes and output nodes.

[0136] Optionally, in one embodiment of the present application, the calculation formula of the mutual attraction in the firefly optimization algorithm-back propagation FA-BP neural network model is:

[0137]

[0138] Where β0 is r ij =0 when the initial attraction, γ is the light absorption coefficient, r ij is the Euclidean distance between individual fireflies;

[0139] The calculation formula of the Euclidean distance between individual fireflies is:

[0140]

[0141] Among them, x id represents the position of firefly i in d-dimensional space, x jdrepresents the position of firefly j in d-dimensional space, and D represents D-dimensional space;

[0142] The firefly position update formula is:

[0143]

[0144] Among them, x j is the position of the firefly j with lower brightness, rand() is the random perturbation term, α is the step size factor, and t is the number of iterations.

[0145] Optionally, in one embodiment of the present application, the calculation formula of the mean absolute percentage error is:

[0146]

[0147] Among them, N is the number of data, t i is the true value, y i is the predicted value;

[0148] The formula for calculating the coefficient of determination is:

[0149]

[0150] Among them, N is the number of data, t i is the true value, y i is the predicted value, is the mean of all true values.

[0151] It should be noted that the above explanation of the embodiment of a method for analyzing the dynamic response of an elastic support structure of a gas turbine cylinder is also applicable to the dynamic response analysis device of an elastic support structure of a gas turbine cylinder of this embodiment, which will not be repeated here.

[0152] According to the dynamic response analysis device of the gas turbine cylinder elastic support structure proposed in the embodiment of the present application, artificial intelligence technology can be used to realize the training and prediction of the dynamic analysis model of the elastic support structure, provide a fast iteration method for design optimization, improve the computational efficiency of the elastic support dynamic simulation in the iterative design process, and realize a dynamic simulation method that takes both efficiency and accuracy into consideration. Thus, the problem in the related technology that the accuracy of the dynamic response and the efficiency of the dynamic response prediction are low, and it is difficult to complete the accurate implementation of the optimization algorithm within the development cycle, is solved.

[0153] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0154] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0155] When the processor 702 executes the program, the dynamic response analysis method of the gas turbine cylinder elastic support structure provided in the above embodiment is implemented.

[0156] Furthermore, the electronic device further comprises:

[0157] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0158] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0159] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0160] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0161] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0162] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0163] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned method for analyzing the dynamic response of a gas turbine cylinder elastic support structure is implemented.

[0164] An embodiment of the present application also provides a computer program product on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for analyzing the dynamic response of a gas turbine cylinder elastic support structure is implemented.

[0165] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0166] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0167] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0168] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0169] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0170] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0171] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0172] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for analyzing the dynamic response of a gas turbine cylinder elastic support structure, characterized in that: The following steps are involved: Generate finite element simulation results of the gas turbine cylinder elastic support structure based on at least one of the isotropic loss factor, structural size, elastic modulus and applied load of the gas turbine cylinder elastic support structure, and extract dynamic response output data of the target machine learning model from the finite element simulation results; Based on the dynamic response output data, a firefly optimization algorithm-back propagation FA-BP neural network model is constructed according to a plurality of parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter; Using the training set to train the FA-BP neural network model to obtain a trained FA-BP neural network model; Based on at least one evaluation index of the mean absolute percentage error and the determination coefficient, the trained FA-BP neural network model is evaluated to obtain an evaluation result, and after the evaluation result meets a preset condition, a dynamic response result of the gas turbine cylinder elastic support structure is generated.

2. The method according to claim 1, characterized in that: The step of extracting the output result of the preset machine learning model from the finite element simulation result comprises: Extracting stress values ​​that meet a preset maximum condition from a plurality of three-dimensional intercept points, and predicting multi-order natural frequencies of the gas turbine cylinder elastic support structure; Based on the stress values ​​that meet the preset maximum conditions among the multiple three-dimensional intercept points and the multi-order natural frequencies of the gas turbine cylinder elastic support structure, the output result of the preset machine learning model is determined.

3. The method according to claim 2, characterized in that The method of constructing a firefly optimization algorithm-back propagation FA-BP neural network model according to a plurality of parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter comprises: Normalize the data in the data set to obtain processed data; Based on the processed data, an input node is generated according to the parameters of the gas turbine cylinder elastic support structure and the at least one external load parameter, and an output node is generated according to the stress values ​​satisfying the preset maximum condition among the multiple three-dimensional intercept points and the multiple-order natural frequencies; The FA-BP neural network model is constructed based on the input nodes and the output nodes.

4. The method according to claim 1, characterized in that The calculation formula of mutual attraction in the firefly optimization algorithm-back propagation FA-BP neural network model is: Where β0 is r ij =0 when the initial attraction, γ is the light absorption coefficient, r ij is the Euclidean distance between individual fireflies; The calculation formula of the Euclidean distance between the fireflies is: Among them, x id represents the position of firefly i in d-dimensional space, x jd represents the position of firefly j in d-dimensional space, and D represents D-dimensional space; The firefly position update formula is: Among them, x j is the position of the firefly j with lower brightness, rand() is the random perturbation term, α is the step size factor, and t is the number of iterations.

5. The method according to claim 1, characterized in that The calculation formula of the mean absolute percentage error is: Where N is the number of data, t i is the true value, y i is the predicted value; The calculation formula of the determination coefficient is: Wherein, N is the number of data, t i is the true value, y i is the predicted value, is the mean of all true values.

6. A dynamic response analysis device for a gas turbine cylinder elastic support structure, characterized in that: include: an extraction module, for generating a finite element simulation result of the gas turbine cylinder elastic support structure based on at least one of an isotropic loss factor, a structural size, an elastic modulus, and an applied load of the gas turbine cylinder elastic support structure, and extracting dynamic response output data of a target machine learning model from the finite element simulation result; A construction module, for constructing a firefly optimization algorithm-back propagation FA-BP neural network model based on the dynamic response output data, according to a plurality of parameters characterizing the gas turbine cylinder elastic support structure and at least one external load parameter; A training module, used for training the FA-BP neural network model using a training set to obtain a trained FA-BP neural network model; An evaluation module is used to evaluate the trained FA-BP neural network model based on at least one evaluation index of a mean absolute percentage error and a determination coefficient to obtain an evaluation result, and after the evaluation result meets a preset condition, generate a dynamic response result of the gas turbine cylinder elastic support structure.

7. The device according to claim 6, characterized in that The extraction module comprises: An extraction unit, used to extract stress values ​​satisfying a preset maximum condition from a plurality of three-dimensional intercept points, and predict multi-order natural frequencies of the gas turbine cylinder elastic support structure; A determination unit is used to determine the output result of the preset machine learning model based on the stress values ​​that meet the preset maximum conditions among the multiple three-dimensional intercept points and the multi-order natural frequencies of the gas turbine cylinder elastic support structure.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for analyzing the dynamic response of a gas turbine cylinder elastic support structure as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a dynamic response analysis method for a gas turbine cylinder elastic support structure as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement a dynamic response analysis method for a gas turbine cylinder elastic support structure as described in any one of claims 1 to 5.

Images